diff --git a/.gitignore b/.gitignore
index 249cda967c11bb62c8affe06d18f26bc5b5f3af0..c2b3cd9535881474da7eee67ab1ec985b36e2cbc 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1 +1,2 @@
-/data
\ No newline at end of file
+/data
+/.vs
\ No newline at end of file
diff --git a/README.md b/README.md
index bb53c6e257d2910f84f798e66a401f9e7c2a7b9e..2e86a47a94707116b710c5ff19900881641ea36f 100644
--- a/README.md
+++ b/README.md
@@ -1,92 +1,2 @@
 # Image classification
-
-
-
-## Getting started
-
-To make it easy for you to get started with GitLab, here's a list of recommended next steps.
-
-Already a pro? Just edit this README.md and make it your own. Want to make it easy? [Use the template at the bottom](#editing-this-readme)!
-
-## Add your files
-
-- [ ] [Create](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#create-a-file) or [upload](https://docs.gitlab.com/ee/user/project/repository/web_editor.html#upload-a-file) files
-- [ ] [Add files using the command line](https://docs.gitlab.com/ee/gitlab-basics/add-file.html#add-a-file-using-the-command-line) or push an existing Git repository with the following command:
-
-```
-cd existing_repo
-git remote add origin https://gitlab.ec-lyon.fr/bdeneuve/image-classification.git
-git branch -M main
-git push -uf origin main
-```
-
-## Integrate with your tools
-
-- [ ] [Set up project integrations](https://gitlab.ec-lyon.fr/bdeneuve/image-classification/-/settings/integrations)
-
-## Collaborate with your team
-
-- [ ] [Invite team members and collaborators](https://docs.gitlab.com/ee/user/project/members/)
-- [ ] [Create a new merge request](https://docs.gitlab.com/ee/user/project/merge_requests/creating_merge_requests.html)
-- [ ] [Automatically close issues from merge requests](https://docs.gitlab.com/ee/user/project/issues/managing_issues.html#closing-issues-automatically)
-- [ ] [Enable merge request approvals](https://docs.gitlab.com/ee/user/project/merge_requests/approvals/)
-- [ ] [Set auto-merge](https://docs.gitlab.com/ee/user/project/merge_requests/merge_when_pipeline_succeeds.html)
-
-## Test and Deploy
-
-Use the built-in continuous integration in GitLab.
-
-- [ ] [Get started with GitLab CI/CD](https://docs.gitlab.com/ee/ci/quick_start/index.html)
-- [ ] [Analyze your code for known vulnerabilities with Static Application Security Testing(SAST)](https://docs.gitlab.com/ee/user/application_security/sast/)
-- [ ] [Deploy to Kubernetes, Amazon EC2, or Amazon ECS using Auto Deploy](https://docs.gitlab.com/ee/topics/autodevops/requirements.html)
-- [ ] [Use pull-based deployments for improved Kubernetes management](https://docs.gitlab.com/ee/user/clusters/agent/)
-- [ ] [Set up protected environments](https://docs.gitlab.com/ee/ci/environments/protected_environments.html)
-
-***
-
-# Editing this README
-
-When you're ready to make this README your own, just edit this file and use the handy template below (or feel free to structure it however you want - this is just a starting point!). Thank you to [makeareadme.com](https://www.makeareadme.com/) for this template.
-
-## Suggestions for a good README
-Every project is different, so consider which of these sections apply to yours. The sections used in the template are suggestions for most open source projects. Also keep in mind that while a README can be too long and detailed, too long is better than too short. If you think your README is too long, consider utilizing another form of documentation rather than cutting out information.
-
-## Name
-Choose a self-explaining name for your project.
-
-## Description
-Let people know what your project can do specifically. Provide context and add a link to any reference visitors might be unfamiliar with. A list of Features or a Background subsection can also be added here. If there are alternatives to your project, this is a good place to list differentiating factors.
-
-## Badges
-On some READMEs, you may see small images that convey metadata, such as whether or not all the tests are passing for the project. You can use Shields to add some to your README. Many services also have instructions for adding a badge.
-
-## Visuals
-Depending on what you are making, it can be a good idea to include screenshots or even a video (you'll frequently see GIFs rather than actual videos). Tools like ttygif can help, but check out Asciinema for a more sophisticated method.
-
-## Installation
-Within a particular ecosystem, there may be a common way of installing things, such as using Yarn, NuGet, or Homebrew. However, consider the possibility that whoever is reading your README is a novice and would like more guidance. Listing specific steps helps remove ambiguity and gets people to using your project as quickly as possible. If it only runs in a specific context like a particular programming language version or operating system or has dependencies that have to be installed manually, also add a Requirements subsection.
-
-## Usage
-Use examples liberally, and show the expected output if you can. It's helpful to have inline the smallest example of usage that you can demonstrate, while providing links to more sophisticated examples if they are too long to reasonably include in the README.
-
-## Support
-Tell people where they can go to for help. It can be any combination of an issue tracker, a chat room, an email address, etc.
-
-## Roadmap
-If you have ideas for releases in the future, it is a good idea to list them in the README.
-
-## Contributing
-State if you are open to contributions and what your requirements are for accepting them.
-
-For people who want to make changes to your project, it's helpful to have some documentation on how to get started. Perhaps there is a script that they should run or some environment variables that they need to set. Make these steps explicit. These instructions could also be useful to your future self.
-
-You can also document commands to lint the code or run tests. These steps help to ensure high code quality and reduce the likelihood that the changes inadvertently break something. Having instructions for running tests is especially helpful if it requires external setup, such as starting a Selenium server for testing in a browser.
-
-## Authors and acknowledgment
-Show your appreciation to those who have contributed to the project.
-
-## License
-For open source projects, say how it is licensed.
-
-## Project status
-If you have run out of energy or time for your project, put a note at the top of the README saying that development has slowed down or stopped completely. Someone may choose to fork your project or volunteer to step in as a maintainer or owner, allowing your project to keep going. You can also make an explicit request for maintainers.
+This project covers the implementation of image classification models in Pyhton. It uses the CIFAR dataset, that is to be prepared before using.It covers two models: k-nearest neighbors (KNN) and neural networks (NN).
\ No newline at end of file
diff --git a/TD1 Brice Deneuve.ipynb b/TD1 Brice Deneuve.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..ad5b4e7cc3fb1ae38ad56e21dc49200604cb1f6a
--- /dev/null
+++ b/TD1 Brice Deneuve.ipynb	
@@ -0,0 +1,620 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Prepare the CIFAR dataset"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## read_cifar_batch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 432x288 with 9 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "import pickle\n",
+    "\n",
+    "def read_cifar_batch(path):\n",
+    "    with open(path, 'rb') as fo:\n",
+    "        dict = pickle.load(fo, encoding='bytes')\n",
+    "\n",
+    "    data=np.array(dict[b'data'],dtype=np.float32)/255\n",
+    "    labels=np.array(dict[b'labels'],dtype=np.int64)\n",
+    "\n",
+    "    return data, labels\n",
+    "\n",
+    "path = r'data/cifar-10-batches-py/data_batch_1'\n",
+    "data, labels = read_cifar_batch(path)\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "fig, axes = plt.subplots(3, 3)\n",
+    "fig.subplots_adjust(hspace=0.6, wspace=0.3)\n",
+    "for i, ax in enumerate(axes.flat):\n",
+    "    ax.imshow(data[i].reshape(3, 32, 32).transpose([1, 2, 0]))\n",
+    "    ax.set_xticks([])\n",
+    "    ax.set_yticks([])\n",
+    "    ax.set_xlabel(labels[i])\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## read_cifar"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 432x288 with 9 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(60000, 3072) (60000,)\n"
+     ]
+    }
+   ],
+   "source": [
+    "import glob \n",
+    "\n",
+    "def read_cifar(path_to_batches_files):\n",
+    "    files = glob.glob(f'{path_to_batches_files}/*_batch*')\n",
+    "    data, labels = read_cifar_batch(files[0])\n",
+    "    for i in range(1,len(files)):\n",
+    "        data_temp,labels_temp = read_cifar_batch(files[i])\n",
+    "        data = np.concatenate((data,data_temp),axis=0)\n",
+    "        labels = np.concatenate((labels,labels_temp),axis=0)\n",
+    "    return data,labels\n",
+    "\n",
+    "# Affiche 9 images alléatoires pour vérifier le bon fonctionnement de la fonction read_cifar\n",
+    "data,labels = read_cifar(\"data/cifar-10-batches-py\")\n",
+    "fig, axes = plt.subplots(3, 3)\n",
+    "fig.subplots_adjust(hspace=0.6, wspace=0.3)\n",
+    "for i, ax in enumerate(axes.flat):\n",
+    "    k = np.random.randint(0,len(data))\n",
+    "    ax.imshow(data[k].reshape(3, 32, 32).transpose([1, 2, 0]))\n",
+    "    ax.set_xticks([])\n",
+    "    ax.set_yticks([])\n",
+    "    ax.set_xlabel(labels[i])\n",
+    "    \n",
+    "plt.show()\n",
+    "print(data.shape,labels.shape)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## split_dataset "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAATcAAAD1CAYAAAA1dbI5AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/Il7ecAAAACXBIWXMAAAsTAAALEwEAmpwYAADEb0lEQVR4nOz92a9t25bmB/1aL8YYs1jVrs45t4zIiIzIRMZpJYllkUoeEhCWjECCFwv4G4yQAIHkF0AChHjwExIIP4AQIIR4gheQEG+WnTKZdmY4o3DGrU+5i7VmNYree2s89DHnWnufvXfEvnnS5+a589Nee601y7Hm6KP1Vnzta2JmnHHGGWd81+C+7QM444wzzvhngbNxO+OMM76TOBu3M8444zuJs3E744wzvpM4G7czzjjjO4nwIQ+OjbfFMgIy3yI4ByICAqUYqkYuBaHe7rw7PdrmZ4oTTA01w8wQAREHGGb1eeIEJ4IBZkZOGQwMwTn52rE55zCrz1ct8+vU253zlFJQVUpWnBNKUkouX3+h33IsLh7Z5dMfvH6jnP77Gt5+l7zlp28Gxn11/7Su7HjfPZzA3Ze/4LB5eT7Hb+ByvbBnj9eYGV7cfL3V6weMaRpJOdP3E1MyihoIxODpmkD09Rp0zuN8wHmPk/oxm1m91kyxBycml1J/F5ntheDEYcZ83SoisF6v0GJMKTONI2ZG27aE4PHBv/Z3TKnw1YsN+0P/1nP8QcZtsYz8rb/zYzBBxCMi9U29Q5wwJGUYE6/udjgB54SLy3X9Yzj+AULTteScSTmTc0bE0TSRlDJaCs57Qgg0TcRMSSnz8sUtpQhmwnKxQgRKKRTNGMbFxSWqyjRNHA4HSinEJrBer1itVuz3B/r9yFdf3NI0Dc///MWHr4rfAlw+/SH/rf/Z/3PedOYF62RelNTvzBvVvKTqxnT8ud4ogEOQ42ZFXQ88METHjet4EVRDKdRHy8lYHe+3+VmGgt2/z/E1yv0BsfLKv/3f+y9/w5/OdwMfP73k3/o3/xuMw55luyT6iA8NqpmiE8+/+oKXrzb8yT/5jF992fNqOzGUzLNHa37vB494svIsmsBifcny4prl+pouBqAatt1+zzgO5Jyr8QJevrpjnBJZBZxHnOfi4grvPGKw2b7CyPydv/O3MRW2m4F/+A//Efv9no8/fsKjxzc8enSDc1YdltDwxfMD/+b/8v/wzr/zg4xbNbjKNBWci4h4ctb7+2LEOUfbRkrJD55pqFbDJuLAwDlPjEIIcX6+IKKYKdOYKVkpuQBKLqV6heW4S3vMIKfMmDJmynolaIGUMqUUzJQYPTF6QhRW6w4Rob1t593ig9bDbw3qOZaT4WI2Ncze9PFB8uDxp8fJa89AENzs2jkRvOO02KtRAhPhTa6lveH5yezBC4JiwPGFHjxPpOZYBJwIiwD+7LO9Fd47lqsO1R7vDXEF1ZFSMkUTy0WHAb/zYyMudlxtBl7c7rm6WLDsWoSCqlGKormgOZFmxwUMB3hxuBAx6sbTxogWGKdESomsmVXnaJct61XD/nDLMGSswHp9wdMnH/Pzn/+ccRy4u9sQgicER4yepmlYxZauafHu3Zm1DzRu1R1VKzgLdQ8tVkNIVxeyOHAOiloNPVUppXpU1cBBu2gJsbqZqqCqpCnXD0sNrC541UIIDieBrlswDIlpSuSS8OII0aE4VKGUhJrivaNtm/ohO6GUxDBUYyoidF3HMIxfu6DOuIf3fvay54UzhxIigBPs5IAdfazXDVu9rf6GCAtveDGCwKRCNqHMLzL7hjWNgB0dsgd2yx48rr66cXqD47Orp+mqQevE6F6PYM54ADPDtNA2kegCIkIpUN1s6LoGEeHRVSE0C56Ohe1uJDhYBGHdBdomsFiuabvF/DoeMyOlCY8QfcD7GnaqKeuVEmMmRuXlqx27zY7dco/3jouPb7g+3HCILdvtnsVizc3NNX/9r/8hz5494fPPP6OUwovnLxBvrFYrVusLYnCnSOFt+CDj9toHBMgxZ3a/xGs46sGrw6SGNsc4PKfqzbng6rp3ghmUorPHVV/PuwgKxQzvq1H1PiBSvTTTggXwXghWjZtankMlw4eav6uGWMk54Vw1tt77934gv/U4GjIc4t4wbvPPJseo8OGZrzhmWE+fsQitzwQxvICKoCoUddVLtGqc6sNtDnnvfbfXt6D7kPgIk/k/MZyDIEbjjLekZc+YccxNe+9x4hCEInZ023HO470Sg2e5cIQmEEPAcoGcaJqG2ESaGAkh4EXwzmFqZOR0jdVN0iimdG2LcwGzQvAHoBpC1UzTRrquQ1XZ7Q5cXo4453j8+BEheHa7LX1/YBx7UhkBmKYJCLzvUv4g46aq5FxwLnDcOp2vnpqfv5sJMQSa2CLiiCGCCZMkUhpRVVz0qBlFC4KjZGWaMinVpONy0cC8R5dSvQJBwAxTxcg4D4tlQ6uRUgpTmupJgzkH6PA+oFpIaaKUESsC4gnR34dYZ7wGAZwPYMc0wr2xOiaCkfvQEmaDJg9/FhSHOMM55aopBAxVyDgKUvNjBnOJqD75obcGr3nX7/K0DbD5wgwOokDESCbo2Tl/K6pDAd4FqgmohUFDMBxlmMijMvUDqrU4eNG0JIwxF7z3hBAR56ofbVqNZJBTYQ+rUZuZUVRp44JUCs4dGIaOlAbQHtOOpgms1heYeX7yk1+Qi/L4yTWPHt1wdXXJMIx8/vmn7A87Xjx/wWF/YLVas1xdP8jMfh0f6LkJwTuiCyyXF4g4drtdDQuwupgRYhNQrQtyShNqhRg9i0WLmdG1DUgtMCy7BW4RuL4MvLzd0B+GUzJbxNcwdYbzjhADahkthprgg1RPzSlm7vQ8kWrcxnEiTYVpSPWYisN7OVV3zngTczX6+FnCXNm6N27HsPAYKh5zXff5uRpiBqdEr2CZYsaYHcqc3gAQQ45l7aN1tHsbZ8cY9TVTOr/BXNk7HYdUr80BBUc2eS13d8ZD1POLwkx3AKibT1ZkLhg2saFMA6VkXFCCBw0eENSMXBTva578eAadHItPx2qoUaxWXH0pTClxebnEKAzTiLjCq1evcNKyXK4oRdlutnz66WesVmvapuX65prdfsPdpsX7arLGcWCxyO8tx39wQSEGT5TIo6srxHnSODCVTDE9JXPDXGgoRZlSqm8UHd61INA0gVwSuWRWi5a2XbJYXjJNhWnM99UzEYrWgkUtPTtiDJilmUbi8D7Oxq2GUtWr9Aj1vpIKg8I05przw7FctMiZ4fdWiBwX6DGXVgsJx59PD3qYY3tg6Oo3Q1Bar7S+QEnkAkMOlAA4wc+7+7GCfoovDMDNldTjUb25OwvYvC7k+GW4uZ6a1ZMx7LyBvRvmTwUdwWEzTSqlQig11dTEhjGPWC4IBScQggeBYiClEIpCqBtNjbWsUkSco4kNBpUepoovmS43KAtCFF5tbjFRnr94wdPHn7DslpjCfn/g008/5Xd+58esVkuury+5vV3TdR1NExEnjOOAWubra+MeH2zcLhct63bNs6tLDOHll0IyJZeMJepKQ2oeLReGNBJcNTTri4YYAiEErFYS+OTxNdE3FBwRENVK8cgJ5wSZQ8wYIk3b4X0HWsPStnU0bcAHx9o1c2HBwDyYw9QRvCO4mgmK3rFctVxcrPhVOGec3wZBCN4/CEuZw4/688kbemjgZtfJuDc2DUbjoREYDhMpK2NxeN/inWBpwkpBSyYuVjgv96VU7qki9efXw1Z54JWJKI5q2JTq7dlcmb1nWJ7xGkwwdZgV1BLFlHEc2Q89h6FnGnoEo4keE8UHx5gT4iKh63BNU5kSBmNWjOmUY3M+zGcDLIR5jRgBQ9TR0eEbT9u1vLh9xe3dHV+8+AV//feVj54848n1Jbv9jj/9kz/n9/7q7xPbwHrd8ujxBf3whN3ujmlKTGPCyjHf/3Z8kHFz4lgtljy+vOZi2VHUWC06Cso0E2et1Fg75UIuhhN3suSnKqjV1/Lec7VaEnxkHJWLRUe/XHIYaihrpoDVXVmU4Cu1wzuHc9BEwXs3G0HBpD5Wc63SZFWcHHOANfnYNPU1zpv6OyBHPtqxQlo95tPdR+7bKRd3/0Q5eVCcwlibiZqCEaTgnM35TsU0oXlEWFbv0OxBKHrvDdox6JmN372RvQ9Xa/puLlSJ4OwclL4LR5YDAkVrgS6lRE6JNCUOhx7nwLluJsM7imaC+DmvrrPX7TBXUIWUE2aKP3rhRs2pO4d4AXF4J/gQUQXnFBGPIdVYTSNpGlgvF0xpYJpGtts7ttslzaNrvK9cWOfcKV+eckZnD/5t+DDj5jxPH3/M7//wh1Ay4zjxvWdPcC9fMeVCsvqGh3EkZUUNlqsLgq9/2DCkWgyI0MXAog189PgRrQ9s7nakZ49ZL1b84stXDNPIOB3mgoWBJbwTYvCslh0hOIKHXGq46czPlR4hWSYXJU+JIMJ62YEWwIiNI8b3l5B/myFACA7Te+N2H47eP6hWpu9zZUdHzosgUuud2RkFQ7wnSqGjUAJk78AKmgd02CAXV3gngJ8vmiNp9/im7t5TMzuFpMf76xY4V25n2khLQeRcUXgbVI1hSnSx0rq0JKZpYhozaVS22x7vqyFyrnJTtRTMFZwr5ClhJngfMRcxB+NYyN7TmKFBcd4jk8PHSAwtLlY+ayyQkpHzSAgdbZNZrpaUPDEOe374/e8DiS+fw5dffApMLLpAKQnv3UwxA98G9uOeXMo7/84PMm45FX75i88p/cgPP3lG2zY8e/qYfpq422xJY0aTkafKVXMIUpiNTkAFTI1+KORUP6RXL19yvV7y6GLJvs8MY6akTJ4yKRmUjHNAG0miiBU86UToy1lRM7yv1A/nPeM4kFJlR8fQEEIkBEcuhSkN5Fywcynt7ZBKsTG5N14nSohxn6sUHiSirYY4mnExIM7hcHOYaNxcXrIIhctW+Xxs2Wa4WQfCoqG57Ng3juSYq5tzV0MtPZwMV/X65/edX32u7VFwqL0eunqxs3f+Dqgq/TCi6mmiQ1yDi0arAaRhmtIcNXm8q95aFxPegyfj/HERKM4KVoRkQlEQV+laTj1+XkveLTgS7808RsSkpVtcYi7imsCT6xuuLy64ulqjNvHD4QmOzGG/5eXLV+x2B/a7PaaGOE9sWvopfXPGrRTlxfNbdBp4dLWa25uWrJYdi6ZhPxQoYLnyybz3NUSZiVFeIiZay8DF8KZM04iWhmXXEr0DU3LK5FwoBawo4iAGKBmyM6ZRKQW0CKqGmqKhEnijCDlX43l0YWP0hOCZUmIYB0p+0Pd2xmuoObb7YkI1bsxcsteNW+UwgpYRzRMlHQj+EvERkQBaC3KLRcdFazxZwebW0ytctI6lBC6k5ZfJzdX1Gpo6OSo6GIVjJ8OxwFAtlqc+xmM4M8rxfqlhl3sta3fGQ5gZwzihFhA3s/xdxEehwdF1i9phNBO5vRNsTv84rIaZc17dtFAUkgre1eseU7wVihdUI0KtwuZi9H1iGDPTZCCBGDsuLmCxXNK0HbGJrFYdTx5dMpmSpontZsfh0NP3AzD3i/tIfxhOBce34cN4bma82mzZbF7iHDx98og/+Gt/lcePr4lNYPrjn2A5sUuJ7z17ytXVJbebLVPKDMPAoyfPMBFuf/ozHj265OMn1/z+7/0+y7ZhGAZ+/vnn/NlPP2Wzz3W3FocSEYNSItkHnEbGCRiNUsYah2CEJtO2DeJD/Qowpglyqr2RaoxTou8nQgivUUzOeIiZkCl65HS+xtQ4tlPVfJqgZWL3k79Pef4p9vmfs/iX/0uEZz/ALp/gDLwJbRSWUbju4HGnBJSPl4WLNnDVXbL9ypP7unlFMaIojWnNx4iRqbSfY73BEDwOV+t8lbairnZlYSiG2IODPuM1FFVe3N5RVHn06BFt09bUj2bMJlzn0ayM04ifoyGsXlsuRpx4SjEO+x1Tqs31YzJijNzcGG10xCCoVlYDLvLZF7e8vNvxp3/6M5BQixNtpHZjFna7wsVyRLXQNfDk8Q1jKUyp8MtffsowjkxjIvoW8QGIfPb5gWHI7/w7P8i4+eC4urlCtKB4+iFxt9kiDparhu998oT1akkTI4+u1qyWHSWNTMERg6cJnmJGFz3rruXmYoWIY8yFF9sD2ykxqB6voDlnUjPI5o2CkkqmOqKVSiBz+KECBSNrweYqK8Wjc2HBFIpCKQ8S0Ge8FTW5P3ttclRhOXLK5N7gYTiUp3ogTi/ptr8ibD5DVwv2N08IVoiWuW4dV62wisLTpbIMcBFhEaDxwk0zk7OzIihuJoXq7DW62g5TK6Ez3eDecHnQue9Vjh2ogpnjbNzeDlXl9m7D7d2O7X7uOAgAac5tz5uEFTKF4I00JiDjJM3GTbm73VX6VlZSqTSxfkosO0fXOG6uV7jQssTo+wP73ZZhGCh4jET/KpFKZpoSq+WS5aLlxctLnj1a8IOPL2mXHbHxwIAVagOBCM6ql7/fJ0r5hjy3pol8/8ffR4ow9T39ZHzx5VfcPL7g+mbNH/7Bj+n3E599+pwmRrwTpHSkUhnjGWHKymXb8PhixdOrS1JW+mniF89fcTtmRhdwrc4VGZ1JnmDeyMwqIljl0/mA9/PC9oY6I1k1bgSPMyhIrQyZkBTUHJYfcqjOeAg5ttIcVTeOdBC5J8weQ1dUCWS+Lz2Pyis+Gn7BFy9/yqZr+OXv/iFLS6z1wCfLNZet46oRFl5IKuRUidrejI8WxsIV0n4gaQ1FxXfVyPo5BzcXCu5P2xwS408mrHr7BnhU5cxzewdUlS++esE/+fNfsbp4RWwamsbhnOKccnGxpGkCbRuJY93s9tuaq05T7VAqWXn1akNKmZQLiCMEx7JzXK4C60UgxI9p2g7noe/37PdblMKUC2Oa+MkvPme77Xlxd6iMhibyvUdL/uCvfEQTfo8f/vj7dG1DEwcGmapwhlhlRRRhtx1Pwh1vwwdWS4X1ZUcbF4jeYFaYph27cSLfbnny+CmLqxXf71qGQ884jHSpI875sd2UwRsff/SI5aohM/Gr518wqTI5ePL9p6yfPiJPI5hiVuoCdYKPAVVFiyKucmqatp2rOWAzoc+AKaWqWqC1Yjv36FCSEhcNWmp+7oy3w3upBclZ6siJcWSNuZN1g6uFcOEiv/83fpfFE2OxGLHvP2F55cnDz5F8wOceVk+ZUuC2hyOrI6XplENr1HOZjY/DxDYFdjmSQ1s3qbk4IdR2qocFUAFCKadm/iIenSkjIu5cUHgHSinsDwcKxmEcsTGx3w9VlCJl2kVbKVa+Uq1EpHb6ZGVKeebJGcMwzc6xsFq1LBctzx6vub5Zsb6+4NFHn/D40SMeP3vCH/41eHa3Y3X9BeYaCpGX+5HdpNz1dwQv+EFI4x3douVHn9/ye3/wh1xfXbI7GFMy+iERfQQJaFH6Q49+UwUFAB8gNA4vAVVPn4QxKzpmxlJqJ0IXsXGgHC8EMyiK5pqkbBqPD4KhHKaJDOCFxaqlXQppqr2NmGK+hkY+BtSqGKb4ypFruvbUfF1KQrVQVPEpVjUSUx4wB9BsxCaQc67N+2d8DccOBXPU8P6YdztSLeT4GGMdjesGLuIFIT9Bdj/EXS4JDYThKyxPkCfGQ4elwOiMED3OCdM01VM8e4imsJBCoiEBZlNNTGupdAOpPZDHRnkRQ2yWNZqpJzbrxVUy8dk1fzeqyEDXRJquQXGMQ2LSzDQWhvFw9AdOG8SUMkWNnPUkNJtTIQRPbAIXVxd03YKLyyuurm+4urlktb6iW6wIseHq5hofWzaHCQkd6iKr9YrYbEnlXqlvPyQOfWIYEzF2LJZrmnZLiPG+Xxyh5FLpKe/5Kz/QuBm5DPRjQc1VvozW5K1TmL56Wcm0GHlMlKlQdiNpP9BvDiQMc0JYetrOsXQdvqvyREULTmqPagjhPontKkO+aasSQYwNEkKVWfJ+PipjGsfK2ZkVQM2MnPMxVTTnYYw8yzD9g/Y/+tAV8VsD7+ew3cPRWrjZ6KlAkMLaJz7uEk+bjE6O/tlHTBdXvLh9ya7f88XPf04TlzTNil/86lOcF2IULtZr2qbh7u4WqGTuISWEet+Sicb3bMeXJBMmC+TFIzSumeK6ditYbbCblwfzURKFWjXlnG17H4IP/OCjJ1yvl3zvBz+gbRf0h8RXX77kq89f8id//ksOY2Is0KdELormSqJvY6RYdRyKFtaLjpubS/7zf/tv8r2Pn/C7P/4+N5cLlotI8JVEvz1kFstLmnbNMBXUR5JzfPyDp9z1A/zxL2jbQBsjNmbcsaPp6oaLm6fE5zskbh7k0o1xnAgB3heAfZBxM2DKBUuFcqpe+bmUXBP3GJhoDRBdbY/xDrrgaJxDpQpK5iExHiZowlzmV0wqdaDWCqpVOla+pmkOU7Xg0kwUMDuxlfNM0r1XdjVE73tU3fzeDkV5d5z+2w6RWd2Feu7u20lrg3UUoxXj2g+4YU8/DPSbV6RpZBgGtoct4zTV57vqYY/jSC6ZYexZLXc0TYMTw/uaZ9kfaj5nuxsIsZkVJyAgODzmQZkIFIpryBIRrc3aQer7ILUNEKrX5lH82Xt7K7x3rJYLpnEkOqELjovHlywbz6PLJd2qoR8TQzH6MZFmL8kJeOfIuZwUgh4/ecSzp4/463/1Rzy6ueLJ9ZroQYoyjrXpfsqZ5WKFc57VYkGSmkf96ONHDCnzn77tibFDcHzxy5/jm8BYlJyrZ79cLlguWro20sRASoa4TNfG17pn3sQHe25TqQnEMpNzm7arZWQvcxhoM89obuORyosJ0eN8pJhxN0yUITHsB6IsMCdzCV9P7ukxN6NHo2cZtGAl4WcvrOQ859zmkGQOn2orjp24WDWW8nNC+hinnhf+u1CT+IanVqOZz4+JEF0NHy9lwPoN+2nH86++YpwGhvHAmNK86YRZY98x9bWl58XLlzTtlqZpuLm+pG0bTIT9oWcYJ8Yhs1p2rJYdy1YI83lzTsEGnCnJLyCsoeTaL9w0OC84D1oUNxOAO6dnTbd3wHvPsmvZutqmFp3j8c0FN5dL8rNrbh6tGVKmn5TDOJFS7WKoWopKyXkmbsNHHz3j448/4g/+yg9YLjqid6RxIKeJYX9gmEb2fc+4HGnbjuvra2T2+j766AYXAmqeooFpLOy3L/Btw1RsNqrGsmvnr0gIDSIF5x1NG986T+WID+a5ZStzqFi9odCFWQK4EnW1KGNKxCbQ+MBF+4i87eltQx4VitFKZNyN7Pcj188eE7tIu4gUK9XAmR3tERL8Sek3iMPD6aJzQYjO46XKMHkfiU2EGEimfLm95VAmDiXhm64aPjVKuVceOeN1iEB0tcUliuFFaXyl/pg4LsuWkLYcdp+yv3vJ2O/IqfYQuthxtVghIqRcydYv93e1aj73emouTDrwy18dSCkxTgPB1ZkZl+trmhBZLZf0+7uqGOI902ZTSd0SaJZr1lePCT4QQ+Squ6HtFjRtx1eTJw0j5eVXPLvuWMi7OVC/zTCMMU9sdgeubowlkcubZzSNJwR48klPTolhqHpuqoV+7ClaSCXPBToj5czV5RWXlxd4Mmk4MOQEJWOaSUNPngbK1PN8twFx3N5u8G2Laxs+efqYp0+e8OPf+TF/9Ef/hF/98gt+8MljLpct4iLPv/iKBmO18FwuIuXRFeIi+37ibjfM/effmCqIVPUGmNsyXI17/b2Wm4gQcYTGE32glQhTAqEOhUlKKcZUSq2SHiYEIcZA4x3iPN7N/pvUyqi4qiPnpeZagpNq5BxE8XgcEY9zniAe8ZEsRlqtcMmhyZisUMygMM93OBu3t0GoSXoTiFKpHgsdyFr1u2x8RUp7yu6OaewppeB8wAdPaCNNqNkw7w3RNLfPOYrzJ09cS+12Mas5meVyQde23Fxfcnm5ZrVacPvqS1JKIEI+zsXAiN7oWBEIRAqNHggp42SgSRGXRnLa4Kd0X0k642tQU4oq+11PDHv2hxFxHaFtWC4XqDZ0jcdm49ZNnqxaxSjmyGkcRxaLlug9aZoAQUvCmYJWZR8tGSuZvj+QknK7GWvOvIlcP3uMn0nBQQciI0+vF3Qx4g1efPUcr5lPPr5BVOnaBsMzpVJl6/37c6sfLHm06AKIwwc/T6E5EjwzwdWKRuc6YgxE72kskA6OTGF3GBiHTJ+FqRSyKk2zQ6fMIgTWl0uWXcOqi7OC7oi52n7VRF9jfoE2eIJ3dE2siWUDhhqJajZ8K0jT8PjJNV/1W7483PGzF1/WftMMem6/eicECK7qsS2YaGzgIr3gsN9x2O+4u3tOSROp1EEi3WJBu1gRfB3gcSQQijjWbYGp0Kc5d+ccKeeTYGnXLVmvl3z09Bmr5YqryzUheMTBH//xP2JztyGXQmyaua2nsF51XHVuJm8nbHxF32dUM14WuFyQtGfYREpO3+pn+RsNAzPHp599wYsXGyR2PPvkMU8/uuF6vaBzAd96mFkIbeqoq6LmUU2V7W5b1Xey0h82QCXy1jqUktJEThNWJnbbLa/u9vz0ly/ox8RYCn/w136X9apj2Tmml69Y68BH3/+Eko3hkPjjf/SP+cWy42/9Z/5TLFYti64lqxE9BFdYdx7/nilAH2Tcgvfc3FxgUuP2o1d1VN6MfpYeDn6uWiplNLIYWYT9OHHYTwxTLT6oKW0Xa24lFRYSuGwWXHVN3TFiRGt3IU30lQvjHc08NzGGGmaaGpOvOnBaCuN2CweHL4nrRcPF449xBtu+5/bQo2rvTUT+NsM740mbkDwSyx5fRnwZcXmA1NPFqp/XSXPq2W0u1rhQvbdjI3MIkTRMpHEijxNL1/HRs0cz8drTtR0xetomcHl5Nevy16EiCHz88ces1yv6Q89qtaJtGqaUWK0WlHmEY52J4ZjSyJRGumZF1fhVDvsd6T0cqN9mqBqpAE4Yp5HDMPIP/sN/yOonKy6uVvzhX/0dbq4u+OjxDU2IONfgY5UpcLiqsOuM5TKSSyGXwt2uFpWmaeBiuaRtArm22ZMUzEXwLfvkOEwwTsrPfvY562XLR4/XXCyWPLu65urimpcvd3x++4qXt1tiCCwuL/j4kxs+enZNCEJwxtWy4dnNmhjebcI+jMTrHav1sjKEj/LE88/i6sQbcR4JnilP5AyaFHWQRehT4TAm0lQHtxhKGhO5TZCVKJ4uRBahwaGYekxr3iSEKncUgiPME7a8g0KpbVeutlg5MWycqpqEExZNpI0LHnVrPI4h1fD0fYnI32Z4gcuQcUyIDsCIacJpwmlGvKcRx6UzvKuE327ZISEivnIIDfAhnIo7wZROjGu5pG1bYox0sZ3VlaFpmlnOptQ8Cka36ChaKKWw6Drapq2DgxF2hwPjUKepOScMY884DKxXSvABFzz9oYbMZ3wd1duq3MBihWFKfPVqg38RabuWRdcxDomuraP8mliJsyJ13ugx5gmNw3KmkMgK/VTYbQ+z/luLYGStk/BwAfORpL5+lcLLlzumYWIVAzerNRfzJmYGu/3A81d7cMLjz58Tu8DF5YL1IiIYi9Zzte4I7+GCfJhxC57l48s61Qo4zkE4tuVQlNrhWZBZgkg1kptA7x13U2E/ZjppaNtI2zi8FNCEWQGpIWiROoSi88v6umZYyXXKDkIz68PFICSXT4OZizpK9lwsl+Rc+PzLl7z48iUHlPjxYwhV8WDMmTMT6u1oRPleeyDJwJQmsiXGkum8R7qOcdiRx4Gv9re0iyWL5YqnlxeE2CLeM05TbdNJieAcFgNtWNfzgzKlQs6FQz/Mg7knplQHdB/2e/pxYBiHOsR36Nlvt6CVjD3l2o0g3vHk0WOaGJnGxO5w4DAMfPLJR7Rz9VRTYRinb/vj/I1EzoW77Z5+nLi6ueRahHWf6IfMMBX+5M9+xk9//jl/9Cc/59ksgPHk0SXL5YLLi9VpGFPwoYrS5kK3vqZI5MXthl98/gLNia4NNNGx6DwWF/guENdXXCyNC4PDbsNkwqevApv+lkVzS9ctuNtNfH6AvawxM/70F8+xIEgwfvf7NzQOumA8WrXE95DxP5jnVuYfTq0tcpSfrlUYm6feFKEqOThwbaS7XBGWLX7IlDETQstq2dK0nuWyY9kGopf7HkYvuCZUkqbVyUlVz5/K1nRu7l6Y+Wzz/U4c0TWIqx7A7nDgeb9nfdlB1yDxXsnzjK/DtJAPW8gTNhzQaWIcDgzjwDCOpGnEtCChJSzXNBeX+NjgQlVVPXJ4VGvCOpfCNCVKKYx5YhgT05TZ7nr2hwOb7Zb9Yc80Jfb7PeM0Mo2VPpBTIo99TT0YZK3rwgcPJjRNw9BPbHY7docDILRtQ4yBcRhO8zvOeB1FC5vtnkPfc7Fe1B7S4Oliph8S4iBNI59/MXC72dN2HU+fXHN1tebpk0e1c8QJ6/Wa4xjIEDoW3ZJH14948eI5+2Hktt+wWra0zRqo7IrVIs6ziY00OHJWdkNiGMZ5LtqGKcNhFHZjVdpVyzx51bC9bhhvGqTxoJkmuvcOevow42aVewJ1AO5RMeKos3EcsDwdZYZwIJ6waLh8esPq0UtSKvT9S5rYcb3uuLhaslh0XK0XtNHhRWvlNQihq5N2AMQ8wpyYDpXXZjNbWYrBPALQeU9sGvAF88LmsOdXX33J9aM1LSsW3UWlsZ/t21uRc2L36gUNhXw4ME0Tu/2efd9zGAYMIYTAcn3F4vFHXFxf45q2bny5TiJXVXJRppzpp8Tt7YZ+GLjbb+n7kWFIfPVyw4uXL/nVp5/y6tUrxnGk7wdKTnMhoJrK6O6nbil1+lnbRgShbVsOh4FXdxs2m12diNS2dF3H3e0dw6z/dcbryKnw4uUrDv2eTz66ZrnwLELLOGaGIXKYlLtdz2effcWrzYFhyjx+csOzp4/40Y8+YdlFFm3L9z56ynKxZNEtWDSBdtGw+l7LNIwcdnu++uol+eaCy6s1AMELN+umzkgpyn5jpFTYHA70+x3T0NPvD8SmY7G85HbM5JLZ2IHHS/hoJRwet7Bo8B5icN8cidcUpqHMRqR6Td67U8+hmqdYlf72rubftBiucSyvOn7w+x9zeb3g52mLxERKO55cP+PyYsXVxRLvDJl6pAEaBzLLHwlVCcTVcLRpIz54YgyUNNUdfr8jTZkpZfa7kWnKvNpsSWY0qyVx0RHaGjqFpuE0Tf2M16ClcPfyOT4PdeE4x3K9Ynl5Bd6zWl7QNi2L5bLm1ZzjMIxMU6LvB16+vOPQ97x89ZLdvmd/6Nnc7ejHkc2+Z78/MPQjt9s79vs9d5tb0jjNfKqqzX+cY3pswTOZxww6VxviEXIpSErVK5wZ88+/fDG37jhyShQ959zeBh8814+uiYdYr19TGm+4CBHH48dXfM8e88MffsIvP3vOi1cbvny+5avPn3P7fEvwdS7JxXrF9dUl11eXXF1csFot+ejZYy4uLlksOnKeOPQH/ugf/xNi0yII45TnOSrGsgsYxt2hR7WeL+88XoRAwemA5cRhGHjxcsenXeCjRyturhZcXy0Q+QaHMgPzrMPj91k94qi1P6ttCR4n4TSg1QfBd8Ll4xXOGXeP13RWPbSmcTTR0TipU+OzQYmgVQP/WI1FjuP9BBf86auUmmRO2RjHTD+MWGYeOlF5Ul3X0bYtoWlqP+rDuQBnfB1WJb99CLUK2ixwscHFhtVyTQiRJjRMOTNNE9vDnr4f2O8PfPXilv3+wPMXL07GbbfdM06JXT9W4zaM7PZ3jONAfzjUnNq8dqB2mRzVJo59osd7jh53zgURIed8Gv47jhP30+rPdJ93QURo2nYeil6jLVCcq4W7ZRdxoeHqOoIVusYxHCaGITP2A6PV19hte/a7nu12z6vlHZcXK1QLl7NK92K1ZpgSh8NEzIogTCmfGu8LQimFnNOs4FOVfIOvSjRRFBUlGwxj5tV24G7TE71wsWrq3I1vksTbNM3sCs4EyZkW4n2dGhnU5lmi81R359BilFx4HK+4frzi8XXH+PKW6XZDX/awn3C5r9NxnCNFR5zzbW2IiPOUud1GqrbNabrVYTvRHwbuXiUOu4HNZksaq6KnGawXa5aLhuXNDXSRHOpA2XO19O2ITeTjH/0YVSU2bd2gRJhyTfq/3OwYxpHNdlfzNoeeF6/uOPQDm92e282Bfkzsdv28wUzkPM2hapl/z4zDHsu5cqJm61Ur6McbZhM1s+GPA6Jtrr71/cg4Vm9xmqY6eSn4OnktpbPc0XtgVkkd69UFWhLjODHGeTRfEyhlJAa4Xndc/vgR4yeXfO/xYza7idtNz75P9OPEZ1+84IvnL/jlZ5+DVcGLi4slP/jh93n65BHf+/5HXPsWFzv2+yoV/tnnXzLNYwQURyrKZjiO6YPVqsP7OvzpkauKv1sPU4Ffvhi5+dUdw5S5WTdz69Y3pOcGzGKGQi4GKN5VQm2c9dbwRpinldeeRDAveBGyaA1nn1wQG0detbCt7PdhGmo1VBzSeCR64r6vQ2KofBw5enC+urO5ZLabPftdzy9/8Zzd9sDd3ZY2CMELXRcQD67zSBAkuLnCe97R3wVV424/kEqhlB1FlWGYGMaphpaHnnGa2O2rpv04Jra7PeM4cRh6doeaEuj7WkSoXlWl/ZjlGn6UCc0Z0zKHoZwM3GkQ9JxncyL3Q7rhJKpQDZg7eW5HA+h9HdsYfOVjnfF1qCrjOFUHoq1E2FSrNYhzdebwNLHf3uFdnUvy9NGCxSLQdkI/FsaU6ZYye+eVnO+co1t23N7dcTgcKKq0XUPbLrhqWpbrhOI5HHoOh57tvqdMGe9rN5IDYlMlsbwY1xdLnMDqUNgeEvs+8cWLLV6MHz1bs1qveF/y/NcwbnNDfKluv5u5TiH4uR+9GqOjRqSaYULVTxPQIIR2SdMF9GJB//MvyP3IMEz4o5RN4xDvcc0BHwpqsD8cTnkXBXIpNUm92bPb9fz0Z8/ZbA7cvdrw+GrJchG5vmppWiFqHT8mrh6Pmp2br96BXJQXd3umnNjvd4zjyN3dgX3fs+sHNn3PNGUOw0jJlYc2jtUbm6aJcUrkrEzTfb7L+0oZMsuYTmiZagucGmitvAlzz9dJheSNsYIPYGqkVPmPJ+NWn1UvDO9o54vkjK9D1ZimCefrkOzgHSmNtUjoBVeUSTOW+spzayI3Vxd0nSM2xlQgFeXiuuHV3Z7buz3bTQJquPv8q5f0fY+a8fjJY773vY9ZLBbVMQktd5s7wt2GISlZhRCsVuAxQnQ1v47y6GpB10QWByV9seHlZuTLlzuCg9vtiG9XpyTE2/Dhxm2Ot5vYABBjJWumKVPyVHsTnasaUHM/olLXrUqdCl5ljQyiw12uSSp8+eWGkI2A4zq2vOxv2X/xnO1QSEWZUsJ5hwt1rpFqnafgfERNeJ4TmzTyauwZtko3BfausAjCInj0y1t8F8m+kpHvL4gzHmJ/OPDv/L2/z74fZ/a50Y95HrJdyCXPFI8888+UaRwppZByLeiUXOVw6ng4ZRhGSs7kcaiJ/lJ7RTFF5jmUzGoyR4NmZq8Zt+P3ozd4JOhq0arQbMY4Dic1mOgW39In+M8B5tYr7yOr1QWNh7tXA7t9HeZ0c7Vm0TZcLhcMiZqS2D+fr2Nh0XY0Kuw2O6L2tG5iCnVIcxCjiw5Nnv3dhv1uz89+8Rk2OybL5YI0pcqVE09oWlpzDH0VUtju9kQvtNHhnNE2wuMQGPrA2Ad2u55Xu8Tne8eekTF9U2Gp1R2zygbZ8SaOg3RLnqqQoHO1vWqmBNQlXj04ZsHDo5VzwGSwGRJ+qsZtUYQJoy+FvWbGoowl4UwQc/dVNG80rcNJIKwbYm6IfYM6RzI4ZKUMmbyfiK8OhEWErhYiznNL3w5TY3/oeXG3rfunwThVheNj3sxmyRqZ1ZJLrjmUnEv15uYp5mrzNPOc0ZzIOVNKrtLQp6nlRx//wTG8kTY4Tbmvgy/vJa2Yx8vNhrEazJouUW3+k/i4/rlFyco0Vy5FquhEKRP9kGibhKkj+kLthlOGPFZ9vhgRqa2TR7mkLngGn+uwlpLwAk2oc0unnDn0E/2UMITlYlE7UUohxoDBSR+uiqLO9DJHlUtzxjI61gvP5dKz38OYlZe7xH5QUvqGZMZVld1mjzg5aZc772tpt1T1gONC1XnBGXWUWNFZ4WO24FWhEkKG/ZT59G5AeqXBs/o4wMLDsiFc1FkIY9/XyVYYMdap8W0XWSwWeB+wRcvysqPrAuN+omRlm2C3mXD7zJQ87apl8WQBsXKyzvg6nHeIF+52B3zsqghkyVgpWClMRy0vFG8ZMSWPAykrY1ZSqVw3U50NWSZNU1WHyAnLdWivPKhmHpME8iDEeGjgTqHpnFLAqEN/OO6xs0ipFkwV1UTO8ZxbfQ/GcWIcRz66WRNdR9su2O0TKcHt3cghFobpxMSiH3tijCyXnjaONT+mDcvgicuGob9jKLWa2gjENtB1C3ZDYjf03N7u6MeJnOaOJoHlsqlyaf5+gPNyucB7CF4pYqgULtcNZYr43HJ7d2DKmf/4s1tSP7Lvx3f+jR9k3FLKvHjxslZCjzce2xOwU/L4tZBvpnIYEOIsYBhkDiWq2mY2o1kuKZrRDLtpwocArUN85d4sfUfJNZzxoSZBnXMM44jZSFEltpGbxzfc6YZhmBhTglSgFF4+v2UxdoTLiBynl5/xNTipOm513kWPiKvMH6ttKTdXK7wDZ5n9bsvY13FwdhQqPYaNOVdRw5LRVJUlKuXjIWpvspi8eevMaTuOFqw/a6liiXmWQrpHfdVc0uzdUQtT55TbW+GcY9k0pDwypYl+FMyUEAMXqyXr1br2haYBZjmz9bqjFDjse26nEVUjxsBysWC5uuAj15CmKko69hMlF5bLjsUiEheR3W5PniayQoiOpvE8ulkSvIAqbRNpmsDlakUIDh/ANY4s0KeBpjGe3rT8YL/m1b7w+VcvmcZcCyHvwAd6boXddlfVT+fKZR3WQQ0TtSaOTw3Lc8dAVQ/xODdPnbRazi+qkI0M+LZBh3oR9SkTCwTCaUhJdP7UmuX9fbI4pZnEaR4fAt2q5bAZZjn02sSNwuHQg6+UFJF7aZ4z3oBZlfC2OkcUEbwLx1EKrLqG6MGZMe0LQxnRMmGltsCZFqwomhNWcq2KztPLOXLZRLB5yMupA2V++yPl48182ykXR40gTt6e3Ht+pVTelnO1Leds294OkaqPqLnOHhGx6rE7x6JrWC0WqGZ2aY+jKhov2sg4FcYhcehHSlG6xZJuGYjNgqvgySnROMdehDQlVotI0IA0gVUXGYdASYW2DXSLhpvrFdELmicWbUtsaueD925Wh0lMRRlSonXCauF5cr2gMPDzr27ZD/re3PkHGjdj7Cc064nv5rycKG9NbOoQFmrS2TC8i/gQiE2sISwwDpmkhaQFSXWKzmRVOcQE9jkTMzRlNl6mmAml1ORz23ZV1pw6pbyUWl/xPhBCW4mnMbL0njhXe25ffIV4mSWSZ0/kjK9hTIXndwdWMaLTgKjSYqhVI7LIO8o08erVC7748jm3my3jmPESiL6hSoeCn1MRxZRClYoHV6dqqWHiqOFk7UMGIcbIse2q5DpCjpkIDhCaWHO2aqSxr6Hugy6EKpoZ6RYd0ZWzWOU7UEphtz9gOfGLT79AguPies1F17JqWja7TTVoiw7vM94ri1ZYdB1Xl2uKPaaocRgnYogYiUUIqIAsWrxAyoUQYhWVbeH3fucTPukT45hZXyy5vFrygx89pmsCHmOae45fvdwwTYlxmtgOla/ax8za12lrP/7BDTePl2Tn+OOf37F7+Q1NnK8Wvyqtms5JXC2noSw6T3+uSed5XJfVxVj35oyaMeRMKtW4kYzcZ4ZhRJNChmJ18JKaUKx+FzzeCeYcYZbLEWc4Z7PccE1+51LVQhVoFh3doqPtGvp9i4tzaANnId53wBDMd/h29nBVq76U1uLBYVb1GBLgIk27QFzC44kuVLEEgzkKpSgUqcWDWoeS08gqm6t2ZZ6TEeepWzoXDo4FiQyzByk0wdH5rg6NKZlS7pvjQ2hnClGD6nTewN4BNWNMBStWUze+clE1F3JbGPapKiR3gUVXO4iihxCFJnhC24ATVqWrdB4zQjGKQXC191ihzkR1DvWBJ4+uURxWjBCF2AjBclVDcLUFzD2UXjBDk9XCRzEOkjFfuHykxOi4uVnSfr5779/5YZJH4k7eWU3q1hD02Nt3RFGbjY9jmjI+BNJUqQTFtEqMzwbOklGGwrgbYRQ8jozgzdXxgVa9Pe9b/Dx0pJvnlRZNFAVH5cJpFsaUmXJ9n4v1kuVqyWLR0h82qFVe1pnc+W6YeGgvcQRoUi0MmGIloSWxGfakVEglEhZXXDQrTEecgTchp1pQKDmdihAlG1i1dnXxViUJs5qayFor6cHX0Yup1ElnRZWkWqutQBtd9R6WK0JqoRRSHk4tWk1YUMSxR9kexqojdsbXoGbsp1pZHlJBKfRp4nAY6ZqGzW2PE+Fi2XJ9tWa97IhOWQKxcVysFjRdJLaecRgY+560HUmqxCAU8xTg9sUdLgTa5Yrvf+8jVqslbQz0h0392m+YzCqdS2cnaK7CiwHJ0ARjgqyJ3kYefZTwbceTJ5d03e17/84PNG5CE1vKzGEyKhMcE8xypYnMXppvAk7cPMEmkcaMVZIcIQTMV9UQLWVuGXR1AE1R9ts9gwaCBczV/sb1ssW5AD5wGDNqGdWJXPLcghERNaQoznsClWxsKFkzTdfUFh3vCE18r1TKbzeEIg3JF4r6OrBHC4QIUWnaJa0p/lpx5CoqOo9c1FJ13LQUprG2XFmp7VBFM1Me56KQonmWxipV0sbMmOQol2V1l1dFtA7+NTMUY9TMPg1EaqJ78v7UWxrKREHoDabQgPPf9of5GwkD1Pl6PWkBrYyGMRsqSlh0OByZQLGOYgtMGtSElBIvnn+BOMWFwrLrWLYdF9dr1ISxCJM5pgLN5Q3jlBinhFDQPGI+Mw5btpuXxBjnnHztbqqtc4W+H9nvDuSSEVerqqJLxFqe3xnZBm4PBw6H90tafRjPbW5vqROkqgvpg+Oo5laKzkKWVWfdeU9RO4WoIIi4mqCWKldS1CFBSCFQvJ7ex4z6HiKAx4eIc1WFIqcaix+HXKjpfJFZJYaGqusms3FTK/joTyHRfWP2GW+F84iLtXSKYjhwdeJYwPBiRGcEOc4GVVQLOWdimmpFu6nGTYviU6qk3xxPBSBLdSOSUnBW6SFqBYrhvOJcLWqIFtyc+pBZpSRLLRoIgoqbOXhGJZhAMQGJtSXljK/BZiciOodzfmbm117PYo6ubXA4UJhyJXFPU8Y7Twx1MLtaQtxEEGPRRELjEQl4qUOhkgkJz+7Qo5ttdXCS4n1gShNTSvhQmQtajJR0FjmtX1Oqa8L5ehoNRylwu82MyXi1nxjH99O5Psxzc0ITI5qNMqvmri66urBMGceEGTjxVZJYhCbfV05tbsXCVcPnvYdUGPcTt+MGFh7Bs3qygggaFRdbQmy4vr6ap2clRstgpaZupMbnOR1qxc6MsABwuKYgvhYpQucxlZPOmJ5DlrdDhNg0xOCZ3FRzlHKc82o4TdXokIg+EB34uaPAgjKGSsvpFjoTdeugkFJKzbOmTM51AlqZ9feLHkUJjxw5Y0r3ah92zOvO6Q7vPL6tslVaQExP+TUBljYP4PYfLnrz24CSC5vNjvVFYNm2eNegmjEJmASur69xAuNh4PlXLxj6gfS9ax5dLZGnF/OU99qV1PcjXg749YKmDSyWC1zTUedyCs4K/UbZbV5hKN265TCNjC6QJyiaGfqelAo5FfrDWI2cBcRlVJTNODKNxjgaL16N9GNmc5hIf0Hi/MMKCrNQYdM6nDnEGaGZW60yhFjDAOeqIanUKJs9vhpTH/tMfagGTovSBMdy2aBFMHPgCzLPSQhO8ZKx0mNFQTNtqCFsVYioCzk4KoGzKL6pbpmPtehgMrPlxWq1zs5u27sgVGUWNZ0biWuuldPA7Xqzd/7EI6vFzpmZacdc2pEfJJj4SulBEHU4dGafK87rPDuhGqijgq9KzffV2kI1rnVGxjwvt5mHERVOzz2aN1MoImfNvnfAOaEJVW23Xa1pmkrj6KfqoAz9UOeT5AnvhbYN4IUstRgoZAQluAiuAd+g4ilU54FxQE3QNNIGeHx1wa4Xxjyx7we2Q22Cd87PPcWOYaqV1N0hnVJbmgVVGKaJYSwMY2HfJ1JWkil/US38g7c27wOxnRvcneKjQ8UQgzCLCjrnZorGvNvPzcwilZ3sm8pjcd6TxwReWCwjuRylyct8UQneFbwIJVW5aeakpamnUKVblMqsNytkLdz3UctJGO9IRzj7a+/HURhBj7p987djhVlnerl37lTdOtI3jLo56ZHDWF8RFTeHuIJ4rY3RAm42SlIKppVRVLQgpcw5t6PBmo3q3NfsRAgxVoJxsFNv6VGwQdVO6iJnfB3eCV107IeJGDyLpiEh9MPA2Gf6w0AMgBZCFIKPSBCKGEMpWE44MS6WDbgGcQ3mPEoVES3T7PGnkcY7mss1Lhi7wfHl9o7tIbMdCs4FvPN0ztXp9n1is5/qJL0QSAlSNm63E/2YGMZMPspizSoy78MHzlA4Llo/q7QCchzOHGs1TCB6h7pKF3HHxeg94kMdsLyIlSKghSHVZufuoplZ58aQp5OX5bwirlC0ClCOY6q5PZ1ZCvOYv24dmBNqs6wRFDPK7A2kkjEF0dr0f17474ZYgZzwKE6OxOvqbTkP7ki8leqZ26nzoOYyZRZRPhb2vfNU0aOCMefXsFPoouYoUvO4RRzqAsSm9pHO3lt9vweS4yevrDYoix25eMCDAeFnfB3LRcNf+d41P/nZS149v2MXG64fXSJO5ijJyDhMhcVqRWw8hzww7CY2B8Wmscq/f9QSAyw6I7g6ND2nEZuvz+hqzj1pqko+Brs+cbcbebVPjGnE4ehc5MWLV+x2B4ahDvVxc67dgDzTTIo4FL03at+kcTu+XuWvHXftIzOltsy4U7IXVKCZ87reOZyvyro+VL5LmQ2QCLjoCaE2zJYhne6r71bm8KRWaWsfKzUEkqpUcCws1BDnaIhflzgybC6G5HPf4Xtx7Aq+7/kUcXNHgeHE8FSpouNYmKOH7GT2uP0c/ls9p3XQTw0XcYI7pQaMYtVLU1eH/YgcPcFjN8OsGDL7ik7cffvVqdvkwRHXri7OVaO3I3jHzeWSF6s9d/tMLsaq1DGJbRtqM3qufdwuZQrKoR/qZHinLHygiREfOnxoToU+cfcULsOqkMKsDJSLkYsxTcY4lTooKBtiniLCYajDaaaUOeY+3NzBUkVj5jX5lzRs8MHGrTLGS6nVMTGIra9hSIEmBvxc3ZgfyrLt5vYsqyGJUwgzsVOFQvXsXBfoloEQQHeFcUqUKWPkmcR7DHHvQ5NjxVVEGMexsuG1zEYRxIU5VALxNW+UylQT3Gd9/XfguBnUFqn6UdZZsV7qJiUoQqFxUgeRUVnvY5rw80yfOiH+KN5RK+YecMFqR8LcoaBaDVhWcCa12ICRdPYQnSPPU89rFddXQ+vmRYacSORlJpE7dzR4Z+P2NkTv+d7TG9Kg/MM/+5JDP7AfRro2sFxe8Olnr0hZccGzPexQCvtDTxM6Vt0Ff+WHP+D6as3V9QWrpaPpPOJ9TVnFllJqSmr3csOUlSFnDqNyGJR9r+z2mf1uwoXa1pdKYUiVrHtsFa2tdvWaPxWWPtAh+eDRfrkUclb8LEvsfQQ8zleCpQ9VIlhnCoiTIx0jEwKINwiKV0fTObr4DNTwrqC2p+hYFXzF1baqeVeuxq0q/jqpF0XOdQ6DSPUY5k+lTsSmkokrZcROIUqMAc16DlneAdWqnSfU5nnVwlSM4Ot0eS8FJzPHzTtsVmotc1iI3QtP6qnC+aYHqEdie914rBoyB7h5MTOP80Pq4GbBzcTwecrZvLkptfEajOCOiRg79bKe8XXkYuQMV1cXXF/dYVJ49fI5q2XLctESQ6VnbDc7XDTEG2IB5yIhRPaHQ1XKvWyJcUG7aOhzYDJPRNgfBoZ+5OXLO1LKTCVzmAq7fmS7HRkHRYufN6SJoR/JKd3HgEeJK6idKr+m9uIHem7H5K1W1QXvEKkGzrnaQBuCxwfmXEldXGoZVPBRKq/SFzwBLLDqrioLPh/o+5GsAybHHbmuW5nDJDfzciQwe486Z5nvg+PTojcoViVwTA1zModL7rzm34PKL6xFHNOC5lJFCGCWjdfZuBlZ6sZSW+U4JfWrgXMwT48/ojbFz8aPGkgeGTmV0l1zZ6fqwvwoJ3X+7enZD3JvxyfPRfnTc85ay+9GLfjAYtGyXAT2g/Di+RYvSnBSNdzEGMcRb4IPgrgWJ9U7m6aJ3gvjVMgKSiCZo6hQCuyHxP4wcrevFI+UM2M2DkNiGBI5VWFLKzV0HcfxJKF2PIkC/9TiFvIhrp6IfAX87J/qHX9z8GMze/ptH8RvGs7n+LuP35Zz/EHG7YwzzjjjnxecWY5nnHHGdxJn43bGGWd8J3E2bmecccZ3Er9xxk1EvIj8fRH5f3zbx3LGNw8R+e+KyB+JyD8Skf+ziHTf9jGd8c1BRDoR+fdE5D+Yz/P/+Ns6lt844wb8d4B//G0fxBnfPETk+8C/AfwtM/sXqILL//q3e1RnfMMYgb9rZn8D+JeAf1VE/pVv40B+o4ybiPwA+NeA/923fSxn/DNDABYiEoAl8Om3fDxnfIOwiqP+d5y/vhVKxm+UcQP+LeB/AH+hmskZ/xzCzH4F/K+AnwOfAXdm9v/6do/qjG8ac2rpHwBfAv9vM/t3v43j+I0xbiLyXwG+NLN//9s+ljP+2UBEboD/GvC7wPeAlYj8t7/dozrjm4aZFTP7l4AfAP+yiPwL38Zx/MYYN+BvA/9VEfkp8H8B/q6I/B+/3UM64xvGfxH4iZl9ZWYJ+L8D/7lv+ZjO+GcEM7sF/r/Av/ptvP9vjHEzs/+Rmf3AzH6HmmT+/5jZeVf/buHnwL8iIkupygX/Bc7Fo+8UROSpiFzPPy+oG9offxvHchaZP+M/MZjZvysi/zfg/wdk4O8D/9tv96jO+IbxCfC/FxFPdZ7+r2b2rdC6zr2lZ5xxxncSvzFh6RlnnHHGN4mzcTvjjDO+kzgbtzPOOOM7ibNxO+OMM76TOBu3M8444zuJs3E744wzvpM4G7czzjjjO4mzcTvjjDO+kzgbtzPOOOM7ibNxO+OMM76TOBu3M8444zuJs3E744wzvpM4G7czzjjjO4mzcTvjjDO+kzgbtzPOOOM7ibNxO+OMM76TOBu3M8444zuJD5IZX19c2eOnH3/tdvnLPFne/quI1J+PN9hr3+5/fkMx2L72w7thr/8HZrx48SW77d1f6tB/m3B588SefvI79ReB+pm9cY7ewDs/RPlLro2/AH8psWj7+lL48tOfsnn1/HyO38BiEe36coETSFnJqkxTxnuHD44QPAClFHx08+2CKZRslKwYhvf+dP06D5hhqvV8GWAOEcGJp2kcIlBKwtQwNYoaakZRCD7gvaOJDsQwlJwULUYuig8eH47K5aBkEOHVy579bnzrOf4g4/b46Uf8D/+n/2sQcFJfTwB5sKrubZSdbhCR+ZCkHrgZ3gneOYL3iBPEyf0qNjAz1OoAUzNDVTGrzzW1+3ew+rqvLWxzp9uOz0G1vr4ZqoX/xf/k3/iQP/23Bk8/+R3+5/+nv4eZIg5EQMTqIhZBHiwjod7vzObHyWzQBLD53Ntrj+f4OrxtXzLM6hvYg8m1qnb/3U7vXB/34EVsXjem9X3++//N/+w//QfyHcTFuuVf/6//DZZtyy+/3HC3H3jxasP6ouXysuPyZoWast0duHqyZHXVcvOkoUzKuCv0+4Sp0C3XtDHQRM96WShpYvvqFh0bNAXIHcF3dM2Sjz/p6Dolla+YdhPjLrM9TOwn5fk28+TxY66v1vzeX7kEEinv+fwXd+y2I6/uJpaXSxZXS4ZeyJZI7GmWC/7t/83fe+ff+eEDYsxABLO64N8Nubd6djR1b9uCbTZmD17/4X2vvfVs3JgN1vHhJ5soX3tuvSDuDdt5G/9LwACTuokImAhuTmDYbFzk6NXZg03GcX/KpJqv4+msvwkyP+Zko3jw+0OD9WBNnM776Vy//tpfN3Df0OfwHUUpyt1+JJfAq01mf1BCXOCcq0Zt26MGU4LDIWNOaBYZLxAauAgNWMRoWSwiq86zaHvSAL0ZKTkYI2YLSmmZtGW3MUouXFxHSAWbEjEFfMqkbKgTaALtegk6wn5CVUk5o8Xo+5GxFH712S1TniAmrm4eUfK757f/GtOvaphyXIhyjD3eWFFyimPevtIMUAydTZIgD4zgA8/v+PtfsGJfu/uht+DqRSA6H89faJR/u2HA7Bifzp4we1KO02dX97j7dfDarnEyWvf3nV7Hjt7dgzd8y8+vn+5qTG3eWE9BgfDaJnfy+t44nDNeh6EMZQ9TYZh2FJRHTy5pWiU2hXEaCbHh0bOn+FZwwTAdcV7oGk+/V1JKjIOHSXDJ4ZIjj5EyrGC6RFJHP4CZA5SSJharTGjARpAshCkTktIUo3OBNkS2mz3oSBoGigDBU6zgTBBxPHpyhVIwn+kWa5x7d9ng1zBu8tr/InLy5t60Yycb8rrleS20sTd+ehCZnr6fvl7bld9mOL8eH4sxh0LzL3pe9n8RTh7S8dzCax+3PLBOD43Um095aGZeM5SnDfHhmx6f9/DMz+9xfE25f5zZMU0xW13kZNzO1u0vgICPBkEJrSFBWK0DPmScL2SF2HrWFwtUCkipqR4TxByalTIZ/S4TNNIY+OLQ5Cmpw0qH6QJMMXWYBaZxwjlj7A0ZgSSQDa9GFxwesKLstge85Hr6nEe8p2A4NZwq3bJBPEhQRN5vvj7YuDkRBDnlYOqH9fXd+xS2HG+0Yw7m/gOe/4K3v5HJHH7eh0IPYp7X3udtF5UcLyp3fNzxgXayxWe8BXaf7zI9emdz8lPuv45nw9547mvnGO4N0ps3vXEOXt+43u6li917avv9gZQSOWcWiwVdt5zf6Hxi/yK0beD7P7pBMJaXgaLQdpGsRtFCt17QtB3LS880FUqBqB0ko0+F6RAZenj52cC0CKRFy74NYJE8LnG2wkvH5WU3pzccEEB7vvz0llggZgFNRC988mRFSgOvvpz48vMtVzcrPvn+E+LScOoYdMc0jQRNPH3U0i1bVusFL17cYVbe+Xd+oHGrBs252XDI/e2vPUpO+zNwTJPcG6dj8ll4YOm+tp7twdVTf3jtAnloMx84j0eDezJuX7O7tVBxxruhs3E75ccE3vT+zeptir2WanPch4dv24/cwzNxDCmBr5/chzHqw2/1+ZvN5mTgnjx5zGKxPHl355zb+xFC4PHja9QmFstMLkZRx2Eo5EHo2g4fIsM4YKXU3KtF8qCkvVByh0yOzjW43JB6j9MGkWrEfLMkhobYxrp+cs3DlewYeo8rjqBwfd3UMLWFKSlFwYUOFzskRjQ4LDhC16GayRSmkmBUUhnp++G96aoP9txqeCenSlnFwzjgaFSEd+2htaj2wPN7Dx4WD06R74OroV4HD8Kk07E9zAu+HuqcvbZ34xj+V2/t/nOdawuv+dnH86IPNjJ9YNFOaVd4zUA9XC21Kn48L+6BXXt4ku5j3uPxbTZbbu/umMaJ5XLJ4ydHj9Dm5fBGBf2ME3wI3NxcUfRAyYWcle2+kPLEwRwxdiAw9D1OBI9AbiiDMGwFT4topPPUMHVyJBY4H/Ax4puW0AZC9JAVNWWaICVhv/VQBG9w86zFLwyLBYqiCrFZ4JsOYsSCx2IgrpakcSCnkZQTWSdSmtD8/o3sg43br5POkDeqq5VacLzvdWPzWgrPahh89NvstGDfOIoHV1E1bDPx5HRBSQ1HTx7i2bq9D2q11OOOpR4B0Tmp/+C8qc3nknJPFXnwOvOzX/u9ABh4B+M4sdsfmKaEd47HTx5x9OdfT8fV1zCt6QZxQtM2LBYdMQSapkFEKFbXic7POuPtcDhat6A4Q91EdoWxD0RJRApigWksPP/iQIOncZ6mWeJzy4LIofeUAkE6Hj15zM3NY3Z9IaWJvt+SS0YmxaVCTplxHPnqxVdM40TrOhzgxNgORkSxKZMsQnQsnqzRpeOF9djNJatHkfUPLxn2e8bdjuH2V6R+z36752LV4d/ThvBrFBQeJIbfsn7ueU33nhO8btjeZVyO1a83DdzDyuu7/ME3X/UNh+FEIXntzc74GgybjdsD78tkvmf2it/YYtzpt9fznw9XQHWwBTl6ewa5KCllSql5k1PRAHmd3jG/0/F+MXDO4b2v6+UUM9t94el8et8JU0Mnq7U1V5MKaRzRXLcRK0aaCvu7EXUt4j3uKiIayOqpaS7Per1muVzRdgv20wFLgBY0K9kgiDKOI5vdjs1+T86F7mI1R21KLkAyTAUNgDNcJ2grjN7wXUeIS9rmMXG5oFku0MNLLCWijywXEe/ffaJ/Dc/tfmd928v+ZZP19wWJdz34Ydh5n0ubf3n4kFOUem++9LWqq5mdvvO+tzwDDMrMC7SjN2b3BN77fOnRyD2k8/Dajvc10u9Dr6/Mxi0XvA+EGB+cxzcOaS42zPUgMMM7T/ARTHDiMK0G823ctzNehxbjcJcoonQXAS2webVhzBm0kKeJYTvy6rM9GgO+9bQXa3KBw5QwE5o28qMf/whxAUUYxp5p6pEyUJKi1IrrbrPhsy+/4NXugA+BH3zcIPRghVRAE6AOIrho2LqgC0hdYH11SdNdsVx/hKSMDRN6+yWtExbB8expJMZvkApyJPvDAzsh97v5Q4N1vxEfb7s3icfF6sRON9dEtJx26odlNXvTnL6WPL4n99Z/9XE6P86oZF5j7m6w+zzeGV+Hzt0czjnswfdaTDoupvvz6E6n9v4zPXpwDws69sBrn6aJlDIijq7rCCGienz8G1WI+Rza3KFQGxAczjmc8/cb39EImrxOKD7jNagqu90BlcIwFrImUkmIhxg9+8OWoU9E8XRxQdus2OwTIgHfdFytV4SmYxgH+n7kcBiYUkE00ehEiBHv3On6UzV8cMTGERpFS6LkAfUOgsOip7lsiRcN1jqIHokenMOAkjM2jJTDgZxH1DIhBLyPyHva438t43ZaesfCwJHmcXyQvMvDk4fr9f715EFu5oFxOnlpdmzLOVq0h8di94v69PwHX/MPRe8vkBPb/Yyv4VTAmTcAkXox3JN3v/7B2YOT/Nr9NQF6//NsAM2MlBKlKE4cIURijK91mxyP5rXj0nrejq181cDdh6xmcloLYueCwrugqozDSLGC+EQhI87w0eOiZ7MZKDkTXSCGhuAbhskIUWjalm65PFVTd7s9282eGAORQrBMKwHvhb7oKbnRNJ7YeMQrWEYlo86DN6zxuGXAr1ssChYE5z04wUSwouSUyMOIlgymeO8A/95z/OsXFF5buPc5meNtf9nIrxwt75sG57WQc/bcjt+13nFP6ZD7lh1qb2HNHXEyZEfSpx5beT70D/9tgYGWgnD0kGrr1fHcHA3dfVV6DkvncHUcE2ZG00Sck69RSLTUPuE01dcJoUFw2FyZfdt5MVNUjXEccSJEF1AVqNRPVIVS7sNSo25mZ7wLyjC+Yrs9cHm1oFs0XH3vKb5tcCFAfkknE25XCKUlZ8dqeUG7WLBcr9js9gzThqHvaULHousIVghWaEqPpIIWz36sF+XNo2vadYMLRp82OJcIXUNfEl4Ci+tL3M0FctWRmoyLHh8DLni8d0Q8aZgYbzeIFbwDr57pUFuz3oVfq6BwxGte2YPkis0Vtnr/vbf29b1U5mrb/Lx5d7fTqx/DGV5f9WJvRkH1AccHz9/d/LjTlwiiYGelp3fCMFRrXboar2NK4Z64/bpxY35s7RvV2bsyvf/ckWOBwMhZKaVQiuK9x/uAWc2Z3RcBXvf3j69XSj3HetzA1GZjafP71hWmx8Vx3sHeCnFGCAXnjLbxtG2gCW4+T1JPhD047zjEVS9pSomcMprzaxQttGAlkdJIHicKjuRbiml9vyg4D8Mw4igYRggtcbHi6ulT3EVEOod6RVxNOdSoEJwq5TAy3G3RKeGy4XCUKc8iGm/HBxm3ulB50DL4IBP2kLjJMedyb87u/bn73Fw1bDMtRNzJ86rPf2DiTtGonYoCBrUj5OiyyX2IewxN7sOVmUZyyt/95Th2v5WwKnUj8xYgInMu7D7fdjR4Tu7zrjK3th0JvMfn6IN2NzVjmjI5ZUq2WRWmAZNTHvdBwuLevs15Gy0K4nBUo1bmLy1GybNhBorWCuo59fB2iBhtp3SDY7VsWCwbcJB13nySUrJhZb7wxOG8oxQl7Q+kqTa1Rx/wrjIKzRIlj+hwYHOYGIrRPHpCETCqIXVOSWVANOOd0bQXLK8f8exHv0MfeiYZyWVCvMM7V9efGpIz02bH7suXxDIhQHCOPJWTYszb8Gvk3B7kQazy0I68ojd6DpAjrWP+3T0wbKdHyexRUZPANUQxRF5XgZjLAUDduasxqxW9e6N476kd3bqTbJIe1SvOxYT3wbCa1wDm/qvKGxR5EJLWhP7RM3fMkkjufgWYGkqpwgUcpapq7iSl4+sf859vrot7EycPNisvVWdMS0FV0bnamnIhl1LzMxwLIvd0ljPehJJzoiRj6idQkJC53Y3cbif2h0IeHOIbgo9E5xnHPU1sWXRLGhfQYqSSwTlUlDY6kICmSAnGZMo09iiKakLdgDhlP+4wMuKUdfMRftHhF6EaRzvgmHCuAZu7WXJh88Vztl+8YP/FS65WSoiBromo09c6Xt7Er5Vz48FitIfZZE6ZtzdQV+gss8U9e/xhqeHBs05hTL3nYWh5PIZT3szuCwd2Kp/aXNUtNQ+jD/zBY27uvO7fDqselpihs4drc/z5MCRF6sISMV6jLh5bqub8ppjd5zuLUUpBteC9Pz3utNm8sekdj0fm1z1+r6FnZb6r1nxcUa0J6Pk+7B0JvDPma6OG9mksiGVC65j6xH7bMyWHlYAPoYaHTqg9nFor4+IQZ5QyOzZitQCAx3xAvaIlUzTVc09mGDImmSGP9XUCtczuBXOKlYxZQigIevLaNGW2L2/pN1tyP0DX4LzgzOEkvDcC+zX03N748bUipj1YjHPo+WDh30fwcDRnYnW3P5aN78Pa+2JFNV5Scy1WFTxP3KeZAlLub6ivV5T9flvDXRdoYry/ds6L/j0wtJRqRI6N887Pu5KbDdvcY8wsWjqfc+fciZDrg0ecgp+FRtUoBXLJqBltjIh3FK0G6jXMqQOOeb0jfacoUGkqWjJaCkWVVApTLkg4rhWdU27nE/02mAk5BUqGzV2mbRwff/+C6JSgE1MCT0O3vMCygGbaZoEXZrJvLQwN44jvIiE0xKbBApS0wFJNDUw64pwRPGx3G6Y8MuqBtmtYhI7MRNI9/fSSojuwHrER7z3BC9pPDJvMf/xHfwybHW4cCES8AKanvNy78OGe28lQfT2EqLdzIvKeiJcP/odj2079cgDy7s6Do2v2wJF7zfs75tiONvbo1U3TwJ//5KdcXl1zfX1NDAGoLTr1Vc8L/20wg1xsXjxvSFo5e+BUGU5qSHr6JB+UKEvOmBTItXCgOufbao9U9QpNSEVPysrAvfd2LFQYWCknJWVBEUr1DEpCi85hagF1p7BUjjnWM94CIRdHP05oUpqYubgeQIVltyCNimnAshGcx4dIiBFUyLnKf5sazgtewJly6Ec0TwxjYsqJohlD6+ZlylQySQvORwxPzuAbkFAYpx2HYUfOI8uFQ4wawr68Y/eiZ/vqFU3OdE7rmnKGj+5URHoXfq0OhfsFLg8qXK+bp9eC0/naqN7ZnLOxB4aQ+9xKfaWHOF4w94veuXnh6vyuAk4Fk+rVFU2M48hPf/YLfvAD5WK94hgwl1Mr0Rlvg1FDPDPF4+cTNX+dPOv66fnZezsF/TPhF8BUq6ggha7zqMKY8omorceqUDlqslUcSbzH7J0YlJSxXGqSWRQolJLRkueqaTVwiKBSj/99uZgzqnEbxsywmwjec/3ogIhn0XYcRMnq0KL4haOJAe89xaqKb5orpU0bcA4cyv7Qk/LElDJTztW4ueq1F02kkimqhCagOFIxXDTwmWna0m9roWLpV5U3a4Xd8x13X23Zb+4geLou1OSWGC548lTeex3/mu1XD43am/fP6/+BAazJZog82JhlrsAdlSAexM5HoweGWvUcTkURq+HNMW+g3FMPjtfLbrNlu70jRsG3EdoFw2xEdfY1zsbtHTBDc5pzV0at8hgiegoToX7OKnNBSexUHHDOY1SSrsmcp/Ghem4pE0LE+0AphomeCkNH7/xIDXLzSnMGJSU0Z1wImDPEGdE7NARU55ahNAFVEaRoQc+e2ztRirG7G9nc7cmj4Cj89Cefcnl5zcX6Gi8dWZXdbmAaCyH0LLo1zkWcxNppItAuGnIa6Q89uWRAiM0SGTOmiVQKSqlFBWrh0HlHtsKkic9efsHWtdy0S7qwYLVcwCTcvdhw+9XnbJ9PTIfMqmuqoGVwiDagDSKRKaWvpzQe4IOpIK8Rdd9i4GpT7Jyrkdd/lwd54uMvx4DkzRzJybjpA0M259h07jJ4SNrU+yeRphFLE0+WC1ZtBz7W++cdXu39/JjfZpgqeRoQ58GHk2GrhgeOmVNgZpCDuXvjplofW0oCqbtsThOq9bt3AfFgWsimc4Gh7kwxxvtQGJ2LG5DTSE6JMlU1Ee+NkjOqpXptmtGcQKpxOxrLc3L17TA1prGAVmVdELQIJUFKhhZQFbRASpVu4dyId0bwMq+Jej2rGWq5TsJyDucDwzSRVcn5eH6OVfc5oSGGWmEYJprBQWEuEgiHu579q4HNV1v6u4wmw1P7+32Q2gkRagdEbEIdLPUO/Bo5t4eEDwCZF+QskDMbLSdvMX5vlPqPxup4S9b78v0pPzcbt1K0fpAPjdLpYjPK/JOzQhoOhDTxNz9+xnB1wxCXaBnQMpKGTSX/HekOZ7wGzZn+7gXtcl1FA92cVTvxCedigvdV1/7UwzmfN60GjpLnEwLDIVGKMQ2ZNkY8AU0jwziw3+9J04T3nkePHhFjQILHqBcGRRkOlQ0/9j3eQRM8ZS4spaykMZBigDIXIVw10vaeXf23GTkr4z4RXYv3Aec8q8UCIdLvlb5XSgLBU2bSdS4Hgp+IMdE0LT4EimbUMkphtV4TYkNsFpgLhNhBD/24p+8PVeDWOUzm6jnKsE0sFx0ruSAWB6Py2Z99weF2YP9yPC2hrg24dkHbNVxcNqzaSNsasVvOufS348OrpQJ6DE9q9r6W4S2dbJfJgw6A+/lwD/JwD82jPqB0PGSzzbfNxu/YNqUnX28ORY+kUWfoNFL6Pb/6/HPSYc94dYXdfoVOA9PU19d2Hhc69OExnnHCMBz4yZ/+I7r1FYuLa3yIWCk1eZ8zTRNrNStEvK/kzqYNNb3ghPyAuX6qoOMoxUipkPs93gVUlX7o2W63TLNxmw4f0bYNsQnkMoJZJWuOiZwSh8MOhxB9oGk7xHmcwG674dXtK3KZcA6axmNFSdP4rX6Wv6lw4li2K9RDpcR6glvUc5QLVtypZVFmKoi4WtnO4wGcoQSKTgxDzzgOFPPEpqVbOgyHbxoYfM1zq+GbOne0WXh8dqTskX0kvTDufrrFW93I7BbiGFkFIVmeA9pMKT1TLsTFJd3Ss1q25PJ1heiH+PV4blSjIyf6Rc2tnPIxVg2ZAXWaw9wAaw8N3L0jZw9DCDnmek6ckJPBs4e5vlPPqIHVvE9OE+Nuw+3dHUN/IC66Oh9VE8M0Yi7gugtCDK8b4DNOyGniq89+xeJyz3qcCLFBSyZPIyVPLLqutk2FQJgH5S4W7XybZxpH1Iww76j1fHls9rKGY7tUMYbZuI3TiHeexhntoqVtI2MaEBHaJhLE13ypJo5cxqZt53kexnA4sNntmKY9TpR2Nm41D3fGm3AitE1X0wkJzBxeIqlk0pRx3EdnD6XJ1Aq5ZGKpif3JYBgGxmHAhZZiggs1XytuJlxbvZ6DqxthiKHStwpY78hiHL4c8JYRVWQQgtaeUtFK8TIxjEKxidAUmoXRrSBNxvsu4w80brXBWdOAZ8RTWMZCEx1N8FyuFnU3lxom1tmHiaJGLkaqasIk1RNVr6ivXQb4E++yyHE4jENnJnw59Q1KvWKqKABmBdNCmgb2m1fcfvoTNG9AMq+mA227oIlrwqMfISEiLqLo/J5nvAktyv72JWWqG4U4P3MIq1pB3zRkLWz7HU0TaWJg3QRijDRNw2a7RU25uLjABY8LgfXqEhDGobDd9oxDqnkT5+icw8pEGib+/D/6jG7Z0S0XaPCEpuHy4oIf//BHPLq+qRy5eVJ5FztKLnz2i88YtlsOL2/Zb74gTwfSsEVEmIb+2/44fyPhnOdisSLnQlBX+YcJxqHQD4mLpcfmXFYuGStzxOMgNMIw7mtKYCpMY5Upj53hvJI0k3Im5cSQJqZUK6i+DQg2qyXXXOzmZU/aeS6c43IRaWPExKG+UGTEz06IxEi3iCxXDc3yksV6xeMn12zu9rXQ9Q58oHEzch5I/Suulp5FE7i5WM1TpwNdDLMsuJ6qmG20E4PcxGNGHbSKoAYpz7mTku/bZxDUZA5Da7dCstr7looxZiXnzDgOTOOekkbKcEDHPTFYJZ0GT1jdENc3dBfXuK6GMYg70bbO+DqcE1bLjuW6w4eAOIeKVC195xCMfkxM45achMEJyQkheEKM7A8Hiin7/q56dt7TX1zhxFOyYxwKpRhiLYSAd5GmrWEuEmhaTxOEYobPBcYJHQZyf2Ccpjn/U4gXV5jCNB4oZUJEaYLDEhyGobaHnXNub4UIBO/xIvgukBJMQx22InU47azY4shWlZnFOZrG0y0j/WGPTqkWDAxkvq7VmAtK9SulRMpVJMEAJ74WjU4k1wTO0cSa6nBOUFdz+M57ROtA6HbZcHV9xfXNFcvVE2LbIa7FucN7/84PrJYa03THsPklH18842Z9yfc+ekLbNDQxkufSbNIjk1zv3VuMtmtwAnnKdeGZcZh6ppQ59KkastmYqQplbrpWYCzKmAp9LvRDT3848PLFc7a3XzLuNzCOXK5XPHv6mC9jCxbpHv+I9dU1q4uLWr2z2XSaqx/wGV+D955Hj6+5vr6EuUzjfJ1TEEOkP+x4dTeheU+fRnJJbHOe6T6OqaRK3MSqXI13rFeXhNAS3IIYFnjf4p3hXIMKLJYN3jesNBDE450nH2q11A8D6e6OQ85sN1tSzkx5ovn+D3AuMBzuKCXhorFadrgycTflKj1+Lpa+A0IMnuAixUWmybjd7cCqV8e8mcXGQ6nRkrjIYtlxfbNCNVO0ULSARLxvqsdlVg2e1Ot/HEfGaarEbWoltVt05JxwIXGIE6ENLFYLoi+zis9MDm4ClibEw+Xlkk8++ZhPvvdDFs0VTQBjROSW953kDzNu00D34gueKCzvemRUNn2m6VqatiFNqVYztSDe1+7+EHC+6jMVA/OeosxkW8XHls43+HAcsmuMY1VpLSnx1cuX7A89rzZbtrsD2/2BwzRW0mZJXF9dsr7+mKePHqNWiaIfTw1JIo9u1pgzrN9BOmBasFK5Vpx39bfCB8/lowsury/IecTUqnflA9F5vEY0tzy9vODFNrMfBrJLcxoBJqsj2FJOBBWiOkqf5j7AQBOXBN/i7jwxRLrY8ujRNV3X0LSBlDJDShxebclTDW8+/UlV2x37oW6Kqnzx0Ue4rmWjhdFBEqEdlDyOTCYE8W+ywc+Y4UTompY2BEowQsgsl4pMAVLExYaihUM/YFZwIjy+uqGY8vzLV2y2O6Y0gYfgHT56xBdwkSa2FB0oxeZ8XGYchc1tIaXC5XU4qWKvrxpWXaRZBdSEooVceiJCUCGIIwTP9fUl19eXXF5dIBZxKEkd+ShL8w58mHFTZdhuIPekoccHT9u1xK4htg1pqiqZYvbAqEVCDIQm0i5XVQxv5oqIdzRdg6pxGCZyyZRcGIaBYZw49AOff/UV+/2Bu+2OQz/QjwNtE2m9o+08T68vuL6+4ZOPPmaaMne7Azl7JhWCDqh6FMGXaW7gVoKEc1j6LsyE6qJKLtW79uGY7zzKtEOYK5WYkS1R5ib2PLfcZE2nIhKl0grAk6n9izIJ0UU0tLStUEpLKQ1pmsjTyH63IaXENIeiqoU0JUQVpzDagFt0TMuWHAMlBvIENiVUC0VfHzJzxkPUinP0HqzgvRGjkM1TiJV0DahYDV2dqyHqmDnsB6Yxk1UrNy0KoamteXWq3ewxz6otJSslC+OgiMtMYyX1FjWapqYhTCoNrPYZl1p5t1BnawRPbMIpbAVAa1W36LsHMsMHGreE8O9/+hl/+h/8O6SxBzUWTZ1X6LzHrHbzR6kfnveeNgSC9zQx0nUtMQQWMfLx0yc8e/aE1ZPHbIaRP/7ZL3hxe8f+cKCfJoZhZHfYk4cBAVaXl1yu11xfXfF3/9bf5OnjG25urvDzANmmaYGqOvGTn/6cL5+/5D/4x/8eq6tHrG8e0y5ucHFBaBfIfGxnfB1ajK++2PDF568oZcKHwONnH80LDvrNhv1hz8vNxGEwpmLs+y0pJ1JOuKbm6cQ7iofiIYkiOATPoUyIOhYWiSWQSmD75atT+sKs8tlVagHDhKoyIQptrdCLKi/2B3RwyLSiWS2JiyV5k5A+QT9QRFBN3+6H+RsKJ0IT/DxAO2GSaZYNFpdIXmHS4TRx6dbz9etQTYxDz3a7w0QRLzRdJDSBMIeviM6yVpmUEl4cQhVTSP1IygOffTbgfJ1c9qPvXdEEx3a7q7McshJ9QVqPtB2rlRBbRy4Tu8OW8PIlVzdXCJmhf0nf7yoN7R34IOMWm5Yf/eG/SOw6nn/2C/r9lnG3hVl+JqcCpkyAlFTj9hhx4vCTx89kvuCEr/o917evWHzxBUmNV5sth6E23u77A6qF1gvdakEIgYurSxww7Hf85M/+jOefLlkvl4QmEkKkaZvZ0gc2w0SaEu3FFcvrJ1w8+giLi8qL8uE1tvQZr8MMylR5bXUMY00TVEFJ47A/MA0jDkd0niKBPhl+bmL2KhwHbttRLmlOUrsj0RuwNlB8IIWmGkOOUvGVXuQeUIvcUZttbkkRM1zlGUFo8MXhhlwlcYaMTiPOu3P71TtQ+7iVpIWMog4kNphGNFcnRQQWXYsHUOXV3S3DkEAK4mftPhFyLmQdiC7gZwki4ygnf+SpFrxXQoQwK/4y94ZbqW15JYGp4H2Hcy0uLDA/UUQ59DuaZkmMa3wUhEwe94xTwt6TXfog4xZiw+/84b/Is+/9kJ/8yX/Iq+df8NUv/5w8jWgaT319VQmgSgkPBUAgy9w2VV3Pdrelff4V7WJJ8IE2BlQdRSt3Jnph2QaarqNpGi6vL9lvd+w3W/70T/6ExjlaX6WMQqyJyrbtWK7XtFc3lNiyuH7M6tEzLh59TH7gGWB2Nm7vghk6VcWN4Gsb1NgPpxzpYbsn54QYeBxRPD7fyyMdjRviMKkN8qa1gyX4mRAqDmkD1kRK19QkNg4rc4++GgE7iZuevtn98AyHA5NZkgfoC3nM6FQVKbz8Uynof+dhpqRcx/upALHFcqVeaCl4Z3RNg+Za8Xx1e1v1+Zw/EXtByLn2kErXEX1bhROspiPUqjayiBKiERtH0/oqmTTryWk2LBUsV8/eSzVu5ltMEsUy0/+/vT+LtSy98vyw3/qGPZzpjjFkRM5MJseqIlkUu1vuttuQWm3ZaMkPNiABlgHDgJ88vhl+95thwA+GAcOyARuy/dCWDUOQrKGhttVoqLq6yKpicSqSyZxivPOZ9vBNfvj2ufdmZkQ2gxVURCfPHxl57zn3nH322cP61vBf/9WsKIoGa1tEB7R4CCv63l+bo/JZPNMVICTGVcmovsPu3iHRO9rVnOD7LHfSrAje43yP6zq6tuGnf/59+naNd90gMJiLCUpnop4j4b2ndz1d0+apSDHijCWkGhMaZN1ydHqG6x3e9dxzfa6qiDAaz6jrMbdfeZ3dap+bN+4yufUK03rCXjHK3oekyzk5m9rt57Sk/U4j+J756fu5tSY4Yop0MWSuU0jEZp0H76aAD46YPIUkKmMzcVc2GlsaFTQqGrRolFKXZFxBoUOJeI3qDEpsNnhiB/qooK9o4FxX8iUmJGSFl5ig6X02vAluvHoXayusrTDWcvzoRy/0WL6sSCnQ+SZ7bVoRUUQ0YgqULWibJSn0NKs1XdvSdT1N24IStDGQJBs5Y1iu1izXS2RvD6MKlFKM6jFaG0ajR4iOqCIwnhnKkeXgcMZq2dEsOvqmwxSGWTWiT5EQQDw0y9yMX03X2DIwmmzUfhLHRydYk5iOhdX68wcBPZtxEzBaEJ1lfiExHtWkmIUDXddmz817XN/RrFe897Mf47oG7/rMvdWW/cMb1OMJdT3Gp1zBDH3HernAdR0ojbEFZTXC2FwpiyFvNwRP27Uksk7+eLJLPZpweOsu0509Jvs3qCY7FGWFMVVuqo7usmC8GTi4tW1PRvCOxfkxMeVjHWOgDy5Xl2OCrocUSSkMk+mhrGpsUlRSXCnBJIXGoJLGKINOCpNM7kdFYaJFvEKhh9mjCqXMZTvdtXaXyyr6RvSSmAhkLpwK2fPQSjHdOaAaTalGs8yxs8ULOYYvOxJZ7CCGyKa3KJG5ZXaYOep8out71k1H12U6hyRADQPPYyI2PV3fZwWYNEgRKSGqTOcpSwu6wKRIMRKKMne2aPH5PhwGEZXWgPf4FJHo8SHggkesH5r0LQlFiImuy/M3RmVJ134+6eEZPTehUDnm3cg+28IgUqDQyHQjQa2IKbBezVGFoXEtx6ePMLpgtrPPV3/vO7z+1pe5+9rbBJ+11i8ujllenNA162yYbIktR1hrc9haFMPUJI/rOkRAG8t4tktZj6jrMZDd3RC6LF4YAklD0jZ7AenKe9vy3J4M13fc/+AvudZoB+KQIUyUGNkIvycUogyVyZI0OyrnaAQgCjqpq9A1GUyyg8FTlM4iQRCv0EqjJBu5SO5GcYNnFjbzEFIipkwq7QehhEjCh4hYg64KDu+8wXTngMnsAMg54i2eACXEQnBtyAIEJHzMs2NH5ZTUdSxjz+l5y3KZPbfNJKoo4dKLavs1MfYkfFbt0AptNN5nef/JrGKiFaqo6P3Q2x03Uv95AIxViumooACcdjT9itB7mqbPIpnKYs0YEYuPiWbtsVrR2oKLs57P0794Rs9NMNpctb/LlS6bXCaAc55GC4zLku/9tb/F+dkxp8ePKYuC8WTG13//20ynO4zqMtMzRpbdaY2/dZsYfV7JlUKJ/oRuf0qbnF3OvQiCNjbLDSfPpgtVq6F5fzOwF7jeuzqwHbZ4AkQSRgU2U8Zg0zU8SMFvOpUHySlJii5EihCJYZPo35yJiE+CTwklHu3DMLZNs/QD0VZnvptSAWMSSXLjdTQlSWVZc6Uy6VqJYIY+R60EK2AUqMJgyhJtCkKItOv1tkPhc5Ak0Yun8d3gASt6rzClx+hh4ReFS0IfhT4oJLis2D/0e4aYcG4galtLUVqKwgyFnNypoFVEWbC10C1z7s4tNMEJRlvKEqpKU5VCqQ0pCG0XcM7S1iM6PDhNYaeAoXcO1ydciIS25cH9JX3/dDrIbxCW6mwnLo3E1YxLLhU7ctJYW8uXvvQuy9UdLi7OqMqCUT3itVdfvyaRlA2YVhMYLmYYqiyDBFL+dfgSV/30l1yalPJAijQ02WrZDKYb9ud6Xnpott4at6chodQnh7akIQN2nTGZZZCGxDFqIGZHVMyBf7hcUjYjAhUqbBLSEVBg8vM2gSYbK5Tk9rmiQAaKkdKbJPbVYqe1IimhMApdWHRRoLTJDfp9n43btlr6VHiJBIlD+6PQ9x2V8YiNl5J9kaxc7aOAT2idhtm0MVdCQ0J0Xmi0yXNJkaH9KuXXKg3GJkRlHUXX9ahoUcpgDVijMCZXUSVlCpn3Qm0Np6sGiRqraxKC854QIHSR9bzl9LTF++dEBVFAZeQThmFjjK5f+pcTk4Bbt29za3hu08B/taKma4l9/wlF8cvczaAIsqElsGm8ZbhxBrqaaD0IV25ec5Vl+yTy421Y+mQkwF8e8/y/pGpEl4iuKItikDzKhkdESM5DiJw1AT0YlEAaDJWgdFbP1QoKbdGmoJjtYMoKXdUUdYU1lrIqUdaiTIHUY0TnQsRmADTAELdeLqPBSO6GUXkQUEgQnUOprXF7GiIJPVLsT3Y4PlnSLnqOHx8TZxVqZ0znO1zyiBWiCH7IsRkrjGqdvfaYWBEQiSifaPsFxgmrcIoXBSZhYknC0Yclpk5UVhFJmJAwKRu8pCJJKdTgidcGXBtpfEssFVIWjE3Bqs/6fxpN0/d88OEJ81X7uef42erlIrmgcN24Df+Ta48FLsfBbZRVlZLLCfHx2jTwS3XeT8mMX9949t7kGiXg+jjo7EEMZPn8kk8yCIYH1/dwe9E/DUoZqvEhohRGZ16g2DHa1ihbUZWDvJHO9eeUIs1yTuwckf5SlEB07kARrYfUgcbqXCSyRUk520UXJbqqKMsSozX20lszYMvs3atLNczLRWszc+FquLYMCefcHSNpk8J4UUfx5YYowZQ56S9Gk0ThXGS1alDpAhc9Pvoc5agsDa5LQ1UppiNLnmGRIGo2DkpZGUwpYDyYnE8dEt5AliS3CVJUiBOUBzEJVMhTstLgkae8vcIIY2XAKvzQdqei0LswDB9yFCO5dG6ehGfz3AQKoz4T0n06zPvkn+OwxG7C2OzGfsYgbqaZP+Fzr2aUbsQs5cpYbRRiGYiBXNfOl6uXDGZ3Ez5vPbcnQ+mC2cFbue+zKrO66niWVU/LmrIsB29K0bsO53pOHt+jXzX0skYPDfS2sKhCo6xB60ywrsoRo9GEsqwoZjvZSxu2p1QuLORxkAIxy18jklV1h/2LKSfBgWFBzLwqIvgY8qjIlMPd7SL2ZCglFKMCiIhVJK3wLjHvV6zmUM0qfMo3rDIKW2hKVTCdGA72KlLoCSFiSJAUoJjMNMXYImVAeUP0AtFCyl51PcmqzgpPbBKpi2ibSCrShJ7NAqXJFfSytJTKkpShvZgTTInRBat2jfMOXQWmlcEUTxd0e8ZqabaoGena89fGLG9cuc3f5PprNs/Jlbd27e/5v81z13Nl1wzWRvDyEytzuvTcGIiDG/qAQI6n01VW8MkmdAuAsp7w9jf+Rm6ZK4rMR6xKGIQQNuGec57QtUTXUe/2lCMHO25Y7RUUBm2zgKVWeSiMtRVlUWFsgalHiFZ5KAK5mwGdL0dBkMvUj7pcx2IaBi+nHO6KbCah5b+rjepz4nIK1xafRUqZWyqiiFEhoinrCt9A37V05w1oQRnN4cEMLQr8OdPasrszhlATXGbHhZiIktjZGaELg4uCNYaitpgkdCnQ9nNCGxETsUZRzAoKZSnLjsJG6iJC4+i6gO96rC6obYVEdTk1zUnA0XCxWuCipx7nyu3nLWDPGJaCVhum2PDU8OB6BfITrxgM2ZX00TUD9okctVwaxs02ryZsXQtLr/8tXRkrSbkKlBkfw+CSeC3a/YQ9k894n1tkaGOZHtxCq01eTaFsFi/cnI8QAkKPirmXuKjHYANSpQ3PhmRNNmxaYdQQltoSYwr0kHfLObnhg7OlypdEEkQNc9Ykc+Zy+1VeIpXeUI42udPhKhhY83l85OD5bfFEbG4lpXKfZ1la8IngIjF5lBhGo5rxaIwtLKFpGZWG8bgg9hGvE13rCSSSSpn5oBX9amAyKChLS/SWrteE3pPbhfNIP1MoytpiTcJacB2ElKXoU4pYnS+NGBO+83gBL4kU+1zRN8Lnt80/c1gqFPpqRUySrpyvTa7l8tBdve6q6HDNzF2+6cmfJXItx0bOtVxex8Pfrg+T2RirPOJv+Dx1+UG5+KBkaAJObNf1J0O0xs6mACSVE8ppmPaTBIIPmWZjDIpcCBCVm+qNqNyFAoShiqZEDQoimaSrdTZ0uQLKFZVIrk1NY8jXDYvgxgtPISEpV1fVsMjmftN8jpUexEhRl4WILZ4MoxRaW0a1oKIhHCS6ytONAkkso8mYO6/dYTqdUhWW9cIiKWJEWJ23dI2narPCrhlZ9nZGdC5wfnyODx6VLLPxHlEsbV/RLk/xdIQU8PWIWI/Y2ZtSlYbSFPiVwgOdWxKCR1JLobLyd7dsoQBdCLt7Fkdi2YGgr8WDT/iOz3xQ9PXw7tPeWv7LZwbiylVYej1qletu3zXP7vJnupqdcBWDXlYVhp+bRt2huVqlPIMhcY0bxyDhA96HT+z/Fp+CMDSy88nzcpkyGAyeDORbyCTplIaZBhqNoBXX+GlqMG46v2bjuCeG9wxXR+LSW+Pqoz+9e5ev3eTkLtMScC39usnFbvFpCKAFNInSCqpWyJ4hTCzRK6Y7E+pxzf7B3kCpAa1rUsjE+OBNziCkSDEuKMcFVSWkGMA3aCJGJ4oyEJNQ6oKAgejwsb8UqiUJ3iUuVmvaVYdrA2VZUmpDWRjEZy5lUWjsuMCOLOd+jqRIUQSU1Wj9nIybCHxSKehabu3a78PM8WsvyX9VcM374lpR4fr/r+ghw/e/UovYEADk6mKWgWvVb5rMhEwXSCk3bg9la+cz+TcStzSBfxauUy82aYXBM9+ctzSEkQlIyrAxMJu8l5YcJl4qgQxkXBnIuJfiBdfzY9cdeeHaApbYdMRs/ng1Q0gGkQkZKrXpclHc4skQAasEkURVCFZpSmNRWLQquXP3NlVdUdUFi3lL2/ZoXRC8xzuogsFawWqopyX1pCSKx7Ue5VtsIVijqMpISkLRFHgMoGnDNackCs4HFucr+mVP6iPTnYrKaiqrcesEMVGWhtGooprWXJwsIAVs5agm5fOrlgpCqdRwoV0vIFxd+Gkow1/2cF7/e8orarjWL3h9dU0bLywmQoqEGHB+mFUa0+VCvZFSiSnmyit5LsOgooIPuc0jpkC6nHuaX+9TREToP4f897uM3Pm58YauLTpxUHhgw2DfyBopxJjL3k91WfW+KiHpa+RbUdc8+JhTG5F4mUPbXDcpfNY8qeEC2BC7U8ppu5xWTqQQBuM5LIPbBeyJKIzllRv7ZEcin7vVekFZTqmrKXt7O3jf8/jxfd577yHHx3NMaTFWU1SG/cmEeqYpkgwE3I71ak2te27tlezt7zAaT0i2YLUUJEZGoSdIzWG5h6QCSZblWUPfdZydLghNQCe4s7tDoaEyAVtrYhA8iigdq3VHkSy2EIo9UGPh82QZn1kVZNNXmJGuNa7GjcN0bZr7lQG8HiL6cG0GabpirGUvK4eQucUjZo8rW7zLCzdeLugb45kGmaXBkMUrFYmN1xdivgHyoBrZruyfh2uZgk1qdIO8SA2GChlyoZvQ9ZM/8ybkE+8Vri10lwWgy7LQQPQZDNzwNxnevHnddQ5bVvvdbOOTudgtngwlQm0LEgGtNTFFXNDYQmGsoCQQg2O9WrFer1g3a1SwFJVFTInoiCk0hQhGJ7SKFDYRChjXmlGpqApIVnCFUFhFkLxsaqtJ0ZK8oW0dfe/RyoAGfe1+3jhIorI3E2MkpIhRFjGGqqzwoj73TP8GQ5nDYETyReV91m+7bohizKYubcIJ2YQeead7ny7DxZiuDKDbbCtseE2CC1eUDqVyLmdwHNBK5demtKkeXIYy13N3CS4no6thcMg21fw0PDlX9UmKz7WUg1zlTjdFgav3bELRT3n417cBAyk3X085ZZC3F4fp9Rvq0MYbS9eumRCujJ5S5qoI8XlCX7/jEBFqbQFFVJ6QAtpACD3r9QpNz3rdcH5yTt/nqXTLtmekoBoVWcbIRrQCoyNGRYxoCgWxixjrkdRQFBWujNgy0HiXlZGjJYVsI5bLBiXC/sEhvu3AO0RDSIHORdRgS9q+JapIUomi2MVUJaNqh/Nu+bnn+dlkxkPkwckKAD+EexsDFQfN/TjcG5vRfokrY2OHELL3V3PjU7rWP7oJV+Nmhc7l4bwmp096E5KToiluqqXXE98DUrrU/Y/XtunDMB9gi88iXRmQTKzOuZlN58F18YLNonPpd8mnjeC1zQ6eVRwukKta0rA6w+VPrm3v6r2fNm6bffpk3TtBluPZeO1bfBYJ6DKRMNncMaS0EHqP7yPrtGa96lmvIuvG03QBbJ6BIUGYny9wa43a2SGqhNcBgwcdKMosNZ585sEZE6lGiV40Khh6NEoXGEr2b+xjrGb/4IC+WRFdh2VJ9JFlmyhEo1IailFC0kIQjRKDNiXG9Z+IDD6NZzJuISbma5dJgPHK+Q/DxRSG4SEwzDC8PJj5Yix0Tig7H675B/GyAyFtXjs8yFkeLl+5uaA3uGIyXd0cSl2rtKZECHm/0rV961y49Bi3+CwuGwDyo08ZtjQoKj/Ju5NPPeYTntz19+RtPolveFUtTUPR4bJD5erd17YTyUKXsrmAroWp23P8RKQEnlys0wkUKC34FAne04un7zyuB+ciLgRMYYHMJ23XLckpZuMd0HmxUyaAyl0Hvsv3m5DQKmGKiImK6DXOqyyGoApGakRZWqa7U/oKQidIs8ZH6GMuTmny0BkZhrD7TZ5XDIph2NRTIM+SdBWRI+CDv+qxfUnwRkrpxoveiZcN23P8xcfvyjl+JuO2xRZbbPHPC7ZE/S222OILia1x22KLLb6Q2Bq3LbbY4guJl8q4ich/TUR+JiK/EJH/+Yveny2eP0TkfyYiPxKRvxCR/5uIVC96n7Z4vhCRXRH5+yLyUxH5iYj8jRexHy+NcRMRDfxvgX8V+Drwb4rI11/sXm3xPCEid4H/MfDdlNI3AQ38Gy92r7b4LeB/A/x/UkpfBf4A+MmL2ImXxrgB3wN+kVJ6L6XUA/934F9/wfu0xfOHAWoRMcAIuP+C92eL5wgRmQH/ZeDfBkgp9Sml8xexLy+TcbsLfHTt8cfDc1t8QZBSugf8r4APgQfARUrpP3qxe7XFc8bbwBHwfxKRH4jI/0FExi9iR14m4/YkqvGWhPcFgojskb3xt4A7wFhE/jsvdq+2eM4wwHeA/11K6dvACngh+fOXybh9DLx27fGrbEOWLxr+ZeBXKaWjlJID/l3gX3zB+7TF88XHwMcppT8aHv99srH7Lxwvk3H7Y+DLIvKWiBTkRPP/+wXv0xbPFx8Cf11ERpIbSP8lXlCyeYvfDlJKD4GPROQrw1P/EvDjF7Evzy559FtCSsmLyP8Q+A/JVbT/Y0rpRy94t7Z4jkgp/ZGI/H3g+4AHfgD871/sXm3xW8D/CPh3BiflPeC/9yJ2YttbusUWW3wh8TKFpVtsscUWzw1b47bFFlt8IbE1bltsscUXElvjtsUWW3whsTVuW2yxxRcSW+O2xRZbfCGxNW5bbLHFFxJb47bFFlt8IbE1bltsscUXElvjtsUWW3whsTVuW2yxxRcSW+O2xRZbfCGxNW5bbLHFFxJb47bFFlt8IbE1bltsscUXElvjtsUWW3whsTVuW2yxxRcSzyQzLiL/xcv2PmkmFvzmc7Hk6r0ppadt/XcWdVWk3Z0ptrCIgAgYLZAgpUTX9YQYCT4A+e9aK5TWGGMuT1cCGFSe849EIm9j82T61M8QE5A/1BhLSgnv+uE16XLL18WjN9tLm/8lLl+7Wvd0vd+e40+hLEwaVYaULg8Z+caQ4fzJ5QFVSiNq8IFSIqZ87lOK+XwN2xDJ/5Ph/ro6t/mBXH3E8OINEinm87g5ryKCUoLRGhEhxkSIkRjj8I5h22nz/JPv45dmhsJnMNxYogGR/MUvb4RP/ft1NqdkOPiSD2SIv6Ud/+cbO9MR//1/6++ye3BAWUJZKA53SmIIeOd4/5f3uJgvOD4+w1pDUWhu3dpnMhmzu7uDGi7cNFx8MSZ8CMQY8SleXqQxBlJMw++RECLNytGHhIvCbP+AFCLLi1Oi64jBkUjElN+T4ubi3mwHUhRihBAiKUX+/X/40xd8NF9OjCvLv/y9L+FiZN17XExENFoMWmkMGhBigHo8wRYlkHCuo2sblss5fd/TdYGYICZQWuf7SwkhDufbeVKMpBDRWvK9bIUkiSTkayEkXBfxLhBDQotQFSXTUc3+3h7WWnrnWTYNq6Yh+M314vHB8+jk4qnf8+U1bglIkq365ZO/+WjTFLMl3E6M+HwoLWiTaNs1iEJQ9H2AEEnek3xL7Fr61RI9qlCmYmdcMq4tI5uAq0VjY7y8BEJKuME7iwlSygtWSooYhBgVVmsulmvaVcN6pdFKGNUar4ToN6/fvCeSEsSoiJfGTRMjRJ1vAKW2TtuToERRmgqTYN2tiN7jkieqRNIJ0YIShTYKIUJ09L6n7zvabk1MDlGJstKkpEHU4IAkeu8uF6swLDgJyd5dghQiMQVCivTOE3zC9YEUsudWakuyYJSl0AWlKbDKQszvd70bFkaN8/pyMX0SXl7j9hlcpQflWoiSH21N1vOCUgpjDE3jUMogKbJY9sS+J/R9vrhCIIbA/OKC1WrOrVs7WCNYXX9q/RFImpgUMYGL4GMYVux45d3p4cK2gg8R5yIKMEoxLgu8SkSvCEPImVLKHkFMg5eQPcQQBgM4GNXPu/B/l1Fow+s7+4QYKTAs+56LpieRvbAQE1EiIkJoG4RE33V473B9nw0fmhATiUiKkUAipEQfPRGIKoEaFrsYiSl7cDHk8x9Cou1zaBtDQsgGVRlz6QUqAa0SikRlQaIiFWWObBP4EPj46PSp3/OlNm5pMF5X//KzW/wWIfkC73tPXVtSVPR9h2s7XNvivCfESELo+p7UReaLBVVl8X5CUViUkk+cJZ0gIhAFCQoVA5EcOibyxZ2SgNYY3WWjlBIKKK1FDV5FSBCHPM7GuKlLzy2hfBo8u0SMOUTa4rNQIkxsQUiJse2IMdGZIW3AEDQlcn4tx/n0XUfwHu89Wpts+ELMBpFElJR99uzEoZJAEqJAvpNj/jmct5yOSMPvCa3y+TIm5261NZSVpSpLtCSsFUqrhrREIvqIDuqfd8/tunHbJI+3+bLfFkJILBctyzXs7e5htMH1axaLlsX8gq4JdH0AbegDtG3Hz37+PvP5AiWJ11+7S1lVxBjYLEiiNAnBxOyZxRjx2l3m25LKi5ioAi0N3uUbqtCWUT3Ga0UMFpcScfAQUsyenw/XcnchZMM25OW2xu3JEKBQQIKRVkSriGIIQ06z9+B8ZNU6vOsJ3uP6nhATIeSiQkwJHwOiAC3YyqKtYlSVpAhE8L0jePAugNJEEuJBQkBCvo99yKbPGIU1htG4ZjIesbc75fXX77A7mzCpC1zf0XUtx+cLlqs1j49O8fHzY7ZnNm6bhPxvD/LJX9NV5UBrjdaawpYYo6jKAqtyhed8vqRzns6FX2fLW//vKUgJ+gg+gQ85bCh0BbLCB2HVdPSdo3OB4CEFxXLec2qW3KsfszOboUUxGVc5DwMkpYAcMuoAMYJWOVQNIV3mVSNCHzyLdQPaoozBWI1CkYKgEIYC3eWqH6LO+dQhyRxTwg9VNNmGpU9EHwL3zxdoEVZdj48RrRQpZqOVPbSA610OF5VB6UQkF4JQCgUUyiAqFwqUVaghV5f98YRSCiksxhqUzmmlmPKilIuo2ftrGneZqtUCKQS6rqXpWmpfsluMKCvLVCbooqKcL1k2PWG5fjqbgt/QuAG/JQN3Lfy8/DVnkZUSykJTVSWjUUVdFuzORtRGIyQ++DgyX7U43xIvTdewret0gS0+FwkIKAIRF3JYYosSEUtMinXT0XUO3wdCgBiEpus5lyVaJe7evsWoKNnfmeSUm0AQfbl1rTfVNXVZ2Ywxh6UuQu+zcRMdKMsSbTQGBTrfUCnlBPWlcfPpcgGMURFipIuRkNh6bk9B7wP3zhYUWiGScn6rNGxoNj74oXoZMMaitSEkQfA5sa8UolVeeJRk701FkJyzTSGQyBVUpVQ+hyb/no2loJSisJYQIqtVS9f2eOczzSQGmqZl1bbUXYUYzWhUMapLjC3RtuD0YknrrqKDJ+FZeW5orYdqyNM9pN8c13Y0ASlSVQXTyYhvfP1d3nz9Lm+8eofd6ZjCCKVOGBwpOD58cMovPnjAP/3hL/jo/mNWTZerOBv6yNa0/VqoRzVvv/MW9+8f431P20bu3Dikd46ud3z44UOaVUNwEd95gkvEoGibwPnZko8/uk9yPXdu7WMKgzIaPxDmhmUxUzjCcB0NxYUQE6HJ9IC27+lcj7UG5x3TwlIaDW6onkdYz9d0bU9ztkBphbKG8St7RC1o50gRtNL/jG/7u4neBz48nlNozbguMFqhXMjFmRRRYhiPa27cmJLQhCScLxe0fU9sG+q6xFiNtdkgkhI+OFKKRFLmSCKIUiitMNYwqidUZcXu3iHj8YzReMrObCfvT+eYn5+zXC55cP9jzs9POT5+xOnFHAT29iYYI9Qji7Gwu1vzza+9zePjM/74z59O93nJcm6b3AtUpWU8rrh5c4+93RnvvP0qd27f4NbNXUaFRUtExR4jGpWE11+9RUBxtmyZL9Z4H+kuiaa/7VD6iwNrDLs7U44enZKCJxEpygKtLaBwztP3nhQSIeRKJSgYQsxm3bBar/HOYwqNMYqUGZ4o4TIn5n32wgSF1irzGlVEKY1SmhAcbgiPpNQYMbRNi+8DvvPMTy9o1y3L8yXGGkxZUE5qVGkplAw0lq3n9iQkwMWESML5SEwgKVNnlNYURYm1lqoq6T1EHy8NlS0MRWkxRqO1yvdVjKSY0wwxBpSoXBywFmMtRVkwne4yqsccHLzCbLbLdLrDzs4eWilCCCz3F6xXSwpbUJQFq2aBUhCip+samtZQNoplsyLGNHiO8vwKCmlDoPytGYocXliruP3KLl/72pt89zvf5MbhPrPxGN93uK7h7PQY33e06wWjSjOqS95+5+vM9va5eesO8/MVKUQeHJ8h2WfeFiF+TVRlwe3DHX75l54kEW0MVV0hStH3jmbd0jQtKimii6SYDaJIvtDW647FfMlqtaKoLUVpL0tBSvKFnHygbR0pgZJ8M4kWjPYUZUVVj5mvLnAu0jQdVGOU1px8dMryYsnybM7xgyPadUvsAmVZUNcVqveMdiaMD3bRY4ve5tyeCBGhsAarFSElgvMkF5lMRkzHI3Z2pohS+JBYtw3r1uG9QxTUdUlZFSitSGFD70gQhBQguoiy2WuuqoJqNGYy3eFg/1Wmkz1u33qVnZ09ZrMdZju7eT9s9uK9d9z7+H1+8csfE2iQ2KJVZLk6J8WG9fqck/k5IjAZj1l37nPv62f23OKQqP2teEMCRWH41ne+ype/8jrf/Re+RlUZUgx8+OgDog8QE5N6QllP2TncY1RoysJgi4IdW1PXM956/Q5N0/Lw5HzY7PYi/3WhBOpCU5Waru2BRFVXGGNISQghV8xSGigcEZQkUhQETd87VquGR48foUthNK0wVZFXfjH0HbjoOTk+oe8DISRG9RilDV1UuN5jtMnnLDsFOB9pQ+D99z5kfrZgfr4k+JhvpiisG8ei9dgPHlKPSpaPTxkd7hCde9GH86WEVoq6rpAYca4nxkBMiXXXkRT05MdN29P2kX6g2CglaKPo2z5ThlzuREhhIO2GQNd11KMKpQ11OWE62WN/7xZ1tYs1I0ia4AOu6+maNdFbSEWufPtcENLGMp5MOT1e0Pdr5otjykJhC8W6bVBKMx5PSdhMVXkKfuOw9HkXFkSgKC2TyYivfPVtvvbNt/jGH7zL6elJJot2KyQJWgzFeMS4HrEzmVJbTaEVhS0wusDoipuHezx8NMsJ7fipVrYtPhciQlkoCqvpu0yRtoVFG5OTxZG8UrPpCkhD94cgonAu0LQt5+dn7B5M8cFhdYnWGiU60wIQlss1TdPRd4F25DG2ICqL9wGjDUZblDK5fcsFuug5OT7n4mzBYr6iGgxi0prQO5LrmZ4tcOsGt25y/sf/NvLC//zjMpnv+uwxhWzMOtcTVaKLjhAjTdvhgyImhVY5DBXILW8pEfzGuCVCyNvpOkdRlpAUZTFiVE2ZjPfQeoSSghgguIjre/q2I8WAkFMcznuapsP7iNYFbe9ZrdY4t8CahDHggkdrS+MCRTEhfI79eWbjllJCRHKTtEi2tn/FUFVrRVlZ/oXv/QFf+/o7/Lf/jb/HdDaiqC0iNZPxDe7cfpfxaMJ4NGU22cEYi9UGRURiILYrkvfE3nHz5gGHDx8jyMCL2oakvy60Eibjism4Zr1eAQmlFaNRze7ubk7Sx4GSEcnEXNGIGLQuaZpzgm/4+OP7THZG7N/cY3Kwg7UFYDBB0C7ifKJtHctFy3rtc9ibhD5ZJpMZ70wOsFpwrePCdyjnEFtRTBXjcsL+rVvYusKhOD875eLslFWtQGsKazh/dIJruxd8NF9SJCBkykdIAU+kj47VuiOuI9oajLHU1YjC5j7T0Ad87+hcgw8+E3yHnGuIOXcXIvgYGc/2sdUuo8lNqnofY2d4lwjBs1gscc7RdT3eZ0LvullxcnzKxcWcew/usW4WrNYXPHq4YrVucHFNUUJZQV1rYoqsm0jv3LDQPhm/kef2fLy1q46Dsqx49dVX+L3f/wbf/vY3uPvKbcqqBKWRUOKdhyRU1Yi6HDGqpxidE88pBVLyBKWIfUegwVqDMdcrZdtiwq8NJSiT+YQiGsRcKn4U1g7hokBSpJjTBJt2mBQTWmXjMpvNmOzsMNmZUU2mGFsQvMKnHuNB2YIkLSEmVAKJQkw53WG0Yrazi5WEdku69QLXrMFolLUoFH1w+A4c4EIPKtHGAAoMFu8CW22EJ0OJMBlVMLJ0rhwMXKLzjs47ep+96+hDpooksiH0geB7UpbxGFY3QEBbi1UGW47YO7jJ7v4hk8k+ZTVBKYuIH1RePB3kCrnPdJPVasnJ8QkX8zlnZ+d0/Zqub3PawkNMhpQUIprJeEJdj5lNDtGq5M/tR0/9nr9xWBr/SiTJK2pASonJdMLXf++b/Ff+9t/ir/21b7O/WyMYiCUHkxwGOe9RyqCVobKj7C0ojaMnRJ89NL3Gp4g2GqXVEI4+g3TIFrkwYA2iNEKBkI2bLQxVadGiUAgpqVxNDTG3EA5hSlUXTMYVd1+9yyt37nD4ym1mh4cw5Nui6uijQZc1YloCghUNyqCSZHUKJdy5dYghsjrqOTpqmJ+ekYxByiyrs1gtiCniY8J7B3iWPtKJIVDShkS/rZA/EUoJhzszxuMSH1oSCSksi6ZhsV5zfD6n6xxd2186MqH3mb8WPHpQ6kHlfLaIQhcjqnrC4c073L79Krt7B+zt30Bri1aaoFNWlvEB7zxNapiTcM6xXq85PTtlsVhwcX6G8x3Od3gXiVEBFYoSoyoO919hf3+fN15/G5LmH/6nP3jq93xm46aUuqyawpBz+bWNx8DMVRo96ITt37zJG19+l+/8V/9Vbrz5TczkJoRVbs5VOi8QOlfVRDRJNEnpIRTSSNKIBMQALhKio2+7nPS83pq6tXG/HgQQRQiR5XKFNRZEKMuCyXSE0pLdtIGtHqMnJoM1lp1pxWt39znYn3Dn9ivszWbUxmJiQLRgC8PIjpiOS77y1bd5eP8RIommyS0+iEJnTgjnR49J3rE4esjRw8fMz89ZNREfEn5oukdyclyJoLQlSqJPcLZq6dbdoA+3xadRFpa337jN7nTE7qSmKAzJlpwuVpwuFvzyg485Pb/gg48f0PWeEAISI1oJRluMVogoki0o6gnlaMrh7deZzvZ45c7rjMcTirLCaHtJ1FZK433eVorhUgrJWMtkMqbt1vSuIdLRuRWrdo62kXFRMJ7ssr+3z8HBPn/4h9/i8PCQV+7coWk7qqp+6vd8ZhKvtXaItQdVh2e0GAJoESZ1wWRc8vrbb/LmO+9w9613qWaHBDXChzYThmWTqBa0NgN3SQ9Cb5vG+vxPdCIR8KGn7zr6rr/8vO0l/iyQy7Yp1/tLAUFbWEbjmrKyGKvxKWvtScoVNFso6tIyHlWMR3XmL/lAu2rQhUEbi9EGbQpKLezvTXFdx3KxZD5f0TuPd5n/5n1geXGe/352wXK5omla2p5B/SMNQpqCHjTERCkCub3Hu4Dzka3j9mRorTjYnbG3M+b2wS5VVRJNxXixZHQxYbXuEdGcnM2Bhq53KJUwSlEaTWF0LjDVE0bTXUazXW7ffY3ZbI9bt+9ibYHWZjhXAecCJNDGEPyg8ZYCMeTwVlKkWFqs1fkeTj29bymLnArZmU052N/n1s3bvHL7NQ4ODzg4uMFyuUTrpxO1n8m4WWvZ29ujbVuapiGEgPf+ia99cjU1oSWxbwLffOcVfu8b7/I3/7X/Frt336Z645tQFDzqhJ6SUnqquMCqGi0lpZkMlA4h0eY+NwJBAomA1hEXOs4vzjk6PuX09Pzys9VGB+xZvuzvMAR1yUnLVdHAeDqmLC23794iAWcnc7QpkZTYvzFjZ1IxnVica7i48Pzq/Z7j02NmH9XcuXuLurKUlaasRpii5HAyYvbmLe7ePmTdOZqm59GDxzx6cMyjByd88Ktf0awammVDDJ44FD5FFMbkCCIrtqqsFDuQdpMPuNWQ13uRB/ElRmEtr919hf2dCXduHVDXFd6O2F017K8a9GjCjZMz6skO9x485uxigXeBwlrGVcV0ukM1GrF/6xXG011Gkx2mu/uURUVdjy/PzUaYNPhMFYkbQb7BIVEixBhwXcfarVj3K5IEUnLE1GMKy2hc8srdW7z+2pu8/tobvHLnDuPxBKsLJKnPval/IxIv5Ivret7tuhFTgyxxunpj/jCtmI4qvvO1t/jOH3ydb33rG3zp7bco9m7R1xVRZVnhPpbEkPC9Y1wIhU6UEnPSmtzAm4hk5ahAwkNwNKsljx4/4vHpCSfzed6X3DpH5JoXJ2xX9aci51Cy0cheXIyR6e4Ok3HNH37vO/zql+/zJ3/0Z3QKUgzU45KiMogRbFVRjGqqyQ7KCM4JrvHgA83SEdJZVggparQtMLZiVNZUE4t55YBmvuBR6GkXS9p1RwzgfBjUdRl0v644ljFGFIJSiRKFRbBKIxK3xu0pSCnh2p448jSrVW6ULxKdy8q6RVExqsfMplNC0kxn+7RtnxcWZdjZ22c0nnBw8xXq0YRqNMmLljFok0USILdq5mLUpvEOUuYP5db6EAdaSbzseFBDLl4SMOi/eedomjXz+QW/eu89yrKiqirWqzV93z/1ez6zcbveU7pZOVP8JJlMREgy1EM3SropUVjD7s6E737nm3z3D/+Ab33r95m8/hq+3OFcWzqyIKFLFT5Guq7FCKiUkCJ7EZIiSTZ+W0IICI4UetarBQ8fPuTRySmn83l+/XCgBoWXDHVV6Nnis9j0EIvkokxM2XO7e/c2f/i97zAaj/npT36OSCR4R1WX2FKTtKDLCjsaU4x2IPb0fY/rAsFF2nbBcrWk63vKsmQ8mbC3t8/45k2KqmI83uXhxwUSHd1qRd96lKlwfigoIeiNpzYIXebCVE5dlJAVRPSgIrLlNz4RMUS6psX3NcvFEt22+DLiUPgkGFNQVTWz6Yx6tIuLsFw2eJ9znrsHh4wnU/YPb1OUFUWZO1jU8G+jByei0EqhtblyeOImVxvxziEBQtBoo9EqK+sqVNaDC4noPX3fs1ouOTs74+zkAq01dV3jvad3z8m4hRC4uLi49N422BgNpRRGa8qyRBlNEqFp1oQQCD7wjW/9AV//2lf4e//Wf5e9gwPK2S6t3SFIVte0JIwItqhxwbB2lvn5OVoabu43lIWmKBRRlTkvpASDQ4WG+dFDPn7vl/zg+3/KRw8fcrpcknRWXpR4TfxagTaK5LbW7WlQ2lIUBcbovMKmnNMyheVrv/dV9vb3iCHx5z/4U+7f+5jxdISSzHH66PGcdLRCf3SKjh0mOdzX3mQ6qaiqgtOzhsXigpuHu5TGolzP8ugRaE0oK0K3YlTpTFVIPV1U9CHSuoAdCghGa1TMfEttNIU21LbArFp0iBgSxaTCmm3j/JMQY+RivgRyR0pSQqdOUUWJKkqq8ZT9/UPuvPYm5XgHbUtOzucsFivOzi8AhSiNsUVWzWVwchI453KKQCT3DAMMJF1S+gSD4bJ66gPErLw8KisYjbGDrrhOmvnpOd2q5ejhY5bLFTHmAqP3kcV88dTv+Rt5btdD0E/QQYanlVJYm/vPfAioGDBF5NU33+CtL3+Zw7tvEFCcNAElAbERVarLpuo2JJq1Zz53LC9aiD0uGMZjw2hkKUpBacGYhKSW2K84ffSQo4cPefjwEeuuxaWYjduw32monMp1Ud8tnoDcRqXUlUzR5VomUNUFu/sz3vrSGzx+eJ+2WWK1wveOtvGcLhs6H4kojPSUynP31gE+RHaoWLc9befoXWS16jiWC0xRoK2l2tOEGPJFbQaqTw8ugI+w2SVJuXCglaIuSsqypC5KlPPoGLEilHV5qSG2xSeRgN5Heh8pCotojS1qdFliyop6NKKsKsbTHarpDtpWeBSiDL2PmXw7cBJzDnxT+MudnpsZeRs5+Dj8vmEvpEF23HtPcB7v3CA0GjFaURQWYkWIIU+/CrmjIcbAer0ihCzW4H38jKN1HX9lscrN7/n5QR0gJqqqoqxKktagBWMN3/3rf51vffs7VId3eO/D+7z34X0OXoHJNHHr1hTvIs4HTk7WXJyuOL5/zsnJBT54plPL/l7F/n7J7Rs9oyoxqTyxvyCszvnJn/6AH//5T/j5z3/Bqm+IxWb/yIMqNkZNkZVctzm3p0AQsYNcUA4hgpchoR9J4hlPLd/8/Xc5O3kMKXDy8ISzxZxHD1f87INjzpcdbYK6CEyrxP7ulFuHU15xM+arhq73LLvA+eKCv3zvEZPJLpPZlC+Nd+l9wMUOKSxRJxbrntYLLirQoBnCnhAolGJnd5fZqGZSlkSrUCRsVWBHNeqn91/soXxJEVOii4mgLaP9A0aTCbODm2hboG0BxuTQX2mMtYgWtMn921U1ouuy1PxGlowYN5rLyJDpTIlM+r3uCG0+P4bch9p2ONfTNGv6riG4Dq0TdZX7UrveZwUQlUUwSQmlB2OaQKnPv4mfmQpijM5yNfFKEjIj2+8QA13fslwucN5hCstkNuPw1g1ee/0Nbt1+JedIrEWNK9qyRIzlLED0Qt8mPvjgfU4ePObBex9TFDcxxQRlx/hzxaKLIIHdqafWLReP7jN/dI8/+dM/55cf3mPZNQQiojbhlGQOnFypum3ljz4PMrRS2SxKGGMWpUxCQuVZBwMlaDwaMZ1MuDAXGGspq6yQbDSYlCcnhZhXc60100mFcyMgcXS6YjHvODpakmTBZDpFJnusFoGoanp3TtcFuqYlikepNHiUOTw+3JsynYx57dXbqJRb8DpV5nma2hBM4tNX6BYZ1lpee/UuN28dsrO3Q1nX1NNdlLEoWxBFD9nsRFKGkFTOnceNLcttU3me6aC6c+mtbe6vdJkXTUOVNEEeEDP869sO73q6ZomoQFVrDm/uQUpopbiYr+i6jvV6Ted6vHe0fQuAsRZtB6HMp+DZxSqVIqpITEPJ8VMhXkxx6B3rSCkxLgtGo5obN25ycHDIzs4uoNDWYuoR3hS0aOZtJHaBft1xdPSYo4f3eHT/fW7cnFLLhN4X9OvIsg9MJh7BcVCvOT0+5vG9+/zy/Y+4f3TK2vmsT3Vd0VfJYOxgmFOx5YV8DkRyTkWJEEQu1W/T5UUsQ+rBDlpvWWm1KAuKQmOtJgTJQz8EtDaDpteY3nXECKePLjg5b7j/aMm6E8aTnjtvXyB4QrI5FPU56YxJiMrUgcIWTCYjbr1yk73dKbdu7+P7jr5vwfisTgGEJNtT/BQYrTk42OfGjUPGszG2LLFVjTIW0ZaozDCtLOKTJg01xGzY0qV6slL68j6KQ69bvGw65tKwXZdKu2rjyp0K3jti9BRWIeMKY/dzUUFpRFtWqzW9czif9f0SOdcqavj5vGTG1cBUFxEcecDH5sslNoYuf1pwnj4l9HKFuins7+4znk4pRiOcsVQ7N7hR7HPWWpZzx8c/f8Ti5BHt/IzFyUe06xXlpGI0q6knJTJKrPpI0wZ++XHgcdFy/vCED/78L7n33k/4/s8esWg6mghukMq5Xi1L4cqd3V71n4chLNUWEYsSMNrmdrikESlJsWe9bmm7POpPKahHBYc3ZrzWHjCdrzk+X2CUUBWKd955m3feusPvf/0Nzs4vOD274NH/9wes+44HJz2LNciJZ/kP/il3b+1y+8aMdZtzQvlkORSJ6XjCO++8zfe+9x3eeOs29cjQtueIyR768emcdduxWK5ZzBvUtqDwRFhruXnzkIPDfbTJxaJ0zTXLVU+NURqPQYeE0ktiirRdw3q9JsREVY1QKiDi2dz3sslrc5WPFyELbISAc5vRkBEhUZWW/d0DJtNb1JWhGhlCiHRd4ON7Dzg/v+CjDz9gsbhgtVxQ1iUhBpbrFeum+dzv+WwFhbyrl7MtU8rzBnOnQsTHeEkgy00EWTWk73PXQAhZ274PiaZXNGthdSHMLxwPPjplfX6KW19QSInVQqoNVkd0WqNDoBq2XUiJToLrCozdZzx9hf0brxHPzlifnWURvZggyuUkns2+56oCINtq6ZORE5MiCu88fe/wPgyLsSbGQNv2PH78mPnFnKZpc2+nJMrKcPPGHpPJiKouKAvNeFRw8+ZNpju7BAzlaMaMgr2DG4yOGkK6n+kcknuIQ4j4QUoHEYraUo0r6rHly196k3feeZt3v/IGo4lB6UhSlmpUUtYVpq7oOs9q3XExX2OL4gUfy5cUAqg8Jk+lrMJL9CRRue1kCCtFVJ4sNpwT7z2ud3R9NxQWybNtxZCvmYFULZ8ycnDZ1eR9ljhSSqgKS10Z9vZrZrOKuraUlcH5QNt4QoDJeIpWivVqQdOsGY1rfAi5D3U+5/vf//lTv+YzFhTyl9ZaDaobcllICCGQBn2onOzLhDzXO9p1w/z8gq539CGySImzBZwcJY4fBc5OGt7/xQPc+hjimrdevUVRJQrtsOKw4Qzbthix1KpgZG9jlYEwZW//bSo7493jFvv+e5ycromuzRWVFElx474Nzfoqryhxq8z7VIhoBEXbdrRtQ9c5QgDB4n3PfL7ml7/8FUdHxyyXS7q+QylFVVve2LlFjMLN0znT6Zid3SmvvfE6k3HNoonUoxnTape7b7zJw+MVohLWZtWRUVmiRQ2J6IhooZqOuHlnxuHNHf723/web77xGu9+9R0eH99j3SyxlWK2O2Fvf4/d/Ty0xgXhfN5Q19WLPpQvKSTLE/mQ0/+btA0qG7gYsmHTDEOyPX3XD9dDS9uu8N7TtR2iBg9f2eztmWFozGXUdNUetAlPjcm5+9nOmJ1Zzd27B0ynNWVt0VrR9571uqeqx3Rtx40bh/Rdi3c948mYECKLxYLHx8f8B//hP3rqt3xGKki2wJseUzV0FITgh3aLQEAuJ0unEIkirBZLHty/z9nJMcuzC4LVNEctZx83nM8tbe+Z3rzNrLhFJZ7+0SNWZyecH92jr+aMCsferhBtRbAV7WwBoyk7+zfYvfkq6sYNjFbcODjEiuKnP/sZ5/M5PqYr9QJzdcC1BvfkrrEtAIYV2HlP7zzOBbrWsVqu+cmPfsjRo4e8/8v3WM8XeNfTti1FaalsyWRSYYuC27cOmc12mEwm/PGf/DkX87zSvv7ma9w4PGR/b487d2/x5S+9wmLeYYzhq195k7pWWCt0q8C67Vn1ga9/6+u8++7rfPsP3mUyroEeHx0+BbTJQppaaUqVlyyrNHpvNgww2eLTUFpR18VAi8pCBajcu52QHPVIQmJitWpYrFrOzxfM5ytWq5Zm1eBcS+eawagV1NUuWluUzqmMTe/v5l8evB2JwWehCxVp2zNOzixni2PqqsjnKyXatmWxWNE5BwKTccXOdMKNvRvs7+9nlZEQeXx0/Pwa5zfYuJ9aq2tuaO4lUxLwyWdLPeS4+r5nPp9zfnrG/Oyc8e4UmiVpeUFaZjbyxCZ2Kk0FnKwvUMsTzOIR1p1hC49WhmhKgqmYt45uvEtlNMVOTVla9nZ3uH3jBm++eodHD+7juo6LdXt5AkVt3OR0pRSyxRMwMP6HsMUHj/Oe1WrF6ckZ9z/+mJOjI5YXF7hhCnkOUbJ4qbaKorRMR5Nh9oLmV+/f59HRMcdn5yxbz507Dd/77gGz2YTXX7/N0cNTlFLcPJxhS43WcDxu8Gia2DEaj5lMp2it8cGzWHvWbUvrHLYwkHLLTx5MkrsUGMRUt3gCUhaOdK4nMXQGYMiz4wNJAqQsQto0DYvFiuVyzXrd0nU9XdvRu4amu0CpTX7WoFWB0sPkKxkKU5Lb+UKIpBgJviMmR0o9p/QYqzg5H+UZxMagBFzvaJoGlwLaaJADxqM8cWtU14OuoML3PeZ5Nc6LMHhsOee2+WmtBaCuKrz3NKs1zuXKFUDbNDx+9Ig/+8GfETz87X9xn932Y9rVe+jjMyIGNT4gnK4I7ZLq/vfZi0t2dhbsVR1GQbsacdTDskv84P4DvC7ZvfUm7777ZW7dvEElHQcTzd/67jfw6wt++UHNH//FzzNvUAlw1bgbw7b96vMgSqGtJhDofM/5/IKf/GTJL//yx7z/lz/CdQ2lSvRNR987YkzDsGTJA0dSpCfx4OP7PHp0zn/2j3/Iyfmcxkfe++iEw/0pb73xBocHB/xr//W/ww//9M9Yr5bceWXKeHePajzjgwc9fn3GerXk4w/uk1zLow/ezxPJZxNa36CN4s6tm/Sd4FsBDKLAKskewrZy9EQ457h/7wHVqMRWJdpa6tEUbSxKG5Tus1Cssjz6+BEPjy74+MEp63XLcrlisTyj71d04eSy5aprVygpIVVZ5BRFusZ521RFvV+zbhas13M+evARve8BYVTnDpaD3Z3cnD8ZIVoyyTisKcQxKoTbh/sYFEWM1H2P+pwb+RmNm6Kua8qyHGghmqquKQqLMYa2aei7DoXKlrd3uA2vpWn40Q9/SNc0vHXrBtXyiFfNQ/bjx9nYrHbxrEiqoXjzglq1zExPSc71dOkWN+KIQ1fyfut4dLHgL3/+U9brC24c7PHWnQNu39jnjVdf4atf+TLKFvzpT9/LnQrhSgY9DzKRrXV7Cvqu5/j4lDgUY/re8eDBQ4g90bX0ywWSPFHDerWm6x0+XSlA9H1PjIl1m7h/74SPPz5ivY44p4lR8B6cy9PIq6pkZ3dCVRm814ynY27cusHuwU3G019QLtYUVUkIOTxanp+hjEKXlqQSRWFoVj1nJ0uOZxeMxlUW1awKlm1Dvx0Q80Q0TcuPf/wziqqgGBXowlLXY4zJo/iMsYOeleHjx0tOzhvOzls65/P5DkJgGOUXehjOvSRL8iNEsqS8DKEuIhRWo7UQU0RUIIkHFXJhTyCknt4n1u2KlHwWPtBC12kePxJ837O4WNCuO2ZlzaEUrE7Oid1z6i1VIoxGIyaTCd55lFLMdnYYjWqqqsrVs/U6TybKSzk+JUIMeO/48Y9/xMX5Kd9+9zW+Mup43S6BD0jeE/wYbxsoe27e9dQ2UBtPaBUxWpy9wYG+wT67/PGDY47XH/DeBz/m/OwRu7MJZfo6e7OKwxv7vP3WG7iYKIzKw4PDprlUcgV1G5c+FV3X8fjR0UDczUqpDx88pF0vaFYL9icFpVFgYL1u6LoOVVbD9KNI2/XQe5pmzf37R3z44SO6NhGDGTpY8kqutMKWltGkxhQKUygmswmHNw+5dfdVpjtT6otl7nJJ0LU9R4+PcN7Rp4AtDVVV0q4cO5MLZpMJBzf2qeqS6c6I8+Wcvt8atyehazt++tNfUJSaYlJm41bVmbdY2CxQiiIkzfEismgSqy7PzQhpwyHMRN+YPDF0+LgmBkvoOpRUQIHWJaI12hqqskYblQndJqFMxNrBu1MMeoyezrXZsEmuqGqVw8/FfMHR42Pm5wv2i5q37Ji0WBO6p5/jZ9NzKwpevfMq4/GY8/NzYozsTGa5ydrmcWxKaarRiLIeEWPk7OyMtm1Ztw3N+Tn3mzX/r//L/5m/+aU9eGuHb+56RpOIlgZKSAYa7zhe9Fycr3n8oGfdadajFnXr66ibY7783X+d8u59jjrF6vwh56s5//E/+mP+/C8/4J/8xS+ICS7mCz4x++hSRmrowdpWS5+I45MT/r1/7z/g7t1XWK86XB/56KP7tOsVXbNmURvGleFwZ5ynJiH0vSOwxsc8vDfExMV5y/37Zzx+fE7fx9yfKkMVXWta5zg+P2OxPGbeNdi64qu/9032btxgNNvhS195A7Ti9OyMw1s3OTyYEVFcLOasLy5o1p7zZc+DB2foJGhRTGZTirpgtFOhKsNy3b7ow/lSwlrDq4cHWXRgNsKWBePxdJAoUjRdy2rd8vDxY87XinWvcJQobTCmYGJGaEpSaumjwqXIMq3y4pUKegckz2xSMJ1UHOzvURYGJLJqIrURRqVhUlaZ9jMIa8RBMQQSsQ8EyTMyut6xXDdofcHJyTEjrfnQlKjOsezWT/2ez+i55bC0KiuKoiCEgDVmGNumhvyWoijKS4XMvu8viw1d19J3LffuPeD9sud26XlnWjOyYJWjcYq2g4+WDWeLjsena46PPK1TdNMLSnVBZS4Y3Xmbye4+N2/d4nFYE3zL8mLOw6MTeh/R1tJ1PSHGK6XgK3G56w+2+BRc3/PgwT20lkErS3K1tA+0nUe8I3rLtC5zS5tkmSrxga7r0UYTI/jggYTRgjGbClxWZFFaaNoWaxPeJGa7+0wmY3Z296hGNcYKBzf2ODvPpM1qVFHVNbowiDEklT2HEBNt05N8AJ9YtQ5dGsp1wWhv8rkzLX+XYbTmcH8XbTRmPBo8t3GePaIUWjSxi5g+UnUROogiGB0pIkyjwRAJQbOOmnU0dCnTq0R6jAaFUJpIqQNWPL5p8wiAbk1wPeIjVhm0VsSkCSoQU8AlsmJjGprnZOhwkJjDYd/jRBDdkjqPe16N80qpS/e1LEpiCFmg7lKrKRP/xuMxZXll4MqqQhvD/Dziuo57x3P+aQqcLdZ885XXsEpT2o57jxP3TiP/8CcnPFr03Ju3+GhJ2mL2V9TLh0zmJd85fJtqLLzz5bexqqMwEHzkYr7g/Q8fXO3wpiTNlabcNRfuWb767wx8cNy7/yuWq3O8S0PFy5BST9cr1s2cfmTZnY4oSoM2mcTtQyQ2jnqcb5B6VDDbrQlEklrRe+gjVLXGWOHk7ISYpsymI77++9/l5s0b7B4coCwkCbzx1h1ciPz4Jz9nNJ1Q1BVJQ9IJjMLqAuUj7bon+JywXp4vSQZoFYeFImzP8RNRlgVf+vIbFNaCKUiiiUljrcEaQzdfceENfTimbzvC2mOSp1Caylp2AU1ireFUDCdSskaTkgOzoLJTCq2Z1g4rS9yy5dGDxzRNnnYmWiFak8wwSS0KBJAomKSJG6I9XPUHq1y06lKiJ7L2nq7p6GJ42td8Vp5bThjn2LwY3Mgcimit2dndzRsdKqmb+aZ937O/v8/R45rVasnZ6RlnfeRnD+f8o5+ccnJrxN94c0LTtTSt5/3jFQ9WgQctjHcm1JMpu3ffoprm+Ze/+NH38a7n4uwxi7NzuqbLbR0xJyFTvKb6cflzm2P7dWCtZjI2LBfniNSklDsVlouG5bJBp0gfsgxR7DzKZx23rAehSXQYm/tM9/YmjMc14+kY5xM+CUontBXe+9X77OzMuHHjkG98c8Rosp8T0ABEqnqUqSRa8fjkiJOzxzw6ecyyaVj3DWU9QQrFaHeCbx2+9fTekzTIRKEr+0KP48sMUQpbTxiNqiwsQe4OSc6T1i3x+BT1+Izp8RlFE7AuUZHFS1Xf05JYp8SvkudUOs6kY2EdwQZUHbF1pCxhPLFYU1KYitPVOY3q6ZueLDqbKHSJUjoLWg60kRRyb3rTNISUJ6tFyWR8iYmkVU6dk4hD3u9peGY9t80Em6zUKrmFg2xoR3V9aeg2r9daU1UVo9EI7x3GGlZt7k9bzVt+9NESHRVfu7WDCzm0nTeO8zZx2mmUqSlGM6rdmxRlgdGGRx+/T9c2dG3Dar6ka7uhRSg3017qf6RPtV1tTq5sJY+eBmsUo8pyfr5Ca0NKhq4JtJ2jc55CEj4kehdRISGSqR8KlYUPBWyI2NJSlJayLFDG4CO4pPDBEaLj4aPHrJuWmDS9B5QFydy6EMD77A364Dm7WOJdy/lyQed6Wu/QBIxS2DrfIMp4cINxqxXK6m3N6GkQha5qyvEoUyliJHmH73t816LmS+x8yWTZMPFQBSiIBBGcCPOYmKfIw9BzLj0X4vCVR0mkMqBsQtuEKnIawliDlAp6he/yuAAhXyuiBm6kLTJnLUK7bujbDtLguaVsZ5KAJBmeZxDvePrXfCbjFmOkaZqBwJsNmPe5O8Ea8xlJkxACy+USYwxVVXHnzh26/oAu9pw+Tlw0Lf/gZxe8fxKoignffWePb9w+4OsfnqKPO86PPNOdMePZBKVAR4fpHauHj7mYzzk+O6YNDhc8vXf0zg9M6E9/400RASCCBp7uzf5Oo7QFd/YOODvumK97nOvxPsvGF1WBd4mVTzw6XVNoQQuoGC8nUCmdibRHRxcondVYpzs7iDYkUZyeXTBfLFitFlh7ygcfHvHGm19msVrydw7/BmfnCx4fnfKf/IN/zK8+/Ig/+4sfYwud5zEEl9uBQqRfLtDWUI9H2KmhNCU0HYmEMkKh9KVo4hafhDKG+uAm9c6UsFqS+pbkHbbvkcWaneWa2DlCWdFJoJXIvd5zEhP3Q+RjScxT4LFb4cThtaeykTIqKirWa0ezWnBx4rIIg5SsuhbnA0rZ3K+aEotmjdGKOlmq2lDXJVVRsrDQuIbUX40AzHP24mU+zgeP64cB0U/Bb+S5xRix1iIil55c1/e0XZen3QxTsUIINE1zWXwYjUcIsDOeEmY9wQXWy4bH646/uH/OzZ0aHce8Ptlh1ay5d7GkwCBBEWNPHwLO+8sm3qZv6bzDx5At+1PnVCaUzrI5ohN2pOjmW+v2NCglKCUE73E+Ihi0FqyyhOgIMbFYNZRaYZRghhVYaT0MlUmkFHIpXwu2qtEWos0rMAAbzbAYadp2yJfe51fvf8wvfvE+f/pnP+bo+ITFfM1kNqYQS9cHfPS5WGEUqIjzLhvWpBCd53nkBm919VlbfAIJSEqjiip7bQjh9AxZO8yyRTc94gLJGGJS9CrSimIZIxcx0hnwBFLTsHGPk5Lcl5oU3pGHv/RdzsOlDhezwGUMQxYtATpPLQso+uBQTmXlEdfiohs8u+ytSXYw2SitxSRcEyV6Ip7ZuDnnSCld5tW6rqPve7q+5+z8PA8EcQ7nHCFkJc2yLLO+W4wU1nJjdy9PLreWDz/6iEdtyz/6+UP2TE1aar42uwn9nPvnnkUwpF6IvqVr17hmhQsRl6ANHV3fXw59TRst8c985YSyAWWFYgSTXc1ps62kPRGD1LtowYWO3nlKW2GswSiDcx2+d5zPG0qtsVpRWjNQPK7m6aUUkIGrZKsRtsp6bHkWQ0ERAkZnpdfOec7OF3z/Bz/mn/yT7/Of/+ff58HDI0KI2LKkqieUZUHXXeBCjw8Obc3Qn9hdaoYZlaOHtu0uh5Bs8VnElFMEYiuM0iQUYeVQFw36dEW5aFGdB2tpVe4xXdvEkshcEtRCgaeYr5EQs9S1zQYzeo3rEr4LNI0bxvptvK58nmS4DmxdINrgiKxcSx8dkhJd29P6NheNUOikhzx6JEbJwqlJEeJzDEuBwXRmWoig6J1nuVqyXK1YrZd454nOEX3WRMdonOtxwWO0pqorqlHJ7GCP8f4MYzSrizmPHz7mhx+eEReJf/Pb7/LWnuX3u5YfemEePc2qZb2cs1qcs1xE1m2Dz7W4rPAxyJtf5deyPLHoTLYuplCNFbs3LDdvT1gdXfym18YXGr3zPDw+Y75a515hBUonUswSNFlgMHvPIUS0CH0APYSgorKWfiIOJEyYNy3ae6Tvcd4RUkQXJosdasWHH3/E2UXmTX788X3mzTKTP5UBDClokh9CzwTB5WlakvKw3z46fB8uVWK974cIY+u5PQneO45PTyiqEpMicbHk7IN7yNEp6uScctGgQ0In4UKEhRL6cYktLQejAj2xeAL1mWKxWrIY7v+286gIyStSUEjSKNEklQdxCrlTyAxV2elsijKKpFNWD4ptth8pT7crC41VFomK4DzWB3waZjKIoCmvzfr4LJ59hgKZ8hF8bp1wztG0Hav1mnXTEL0nOTdoqkUoLCFGQkqsyjqvpkpywtkWzHZ2IMH58TnzNnCyaLEYptZyY1RQrkGlzKFqmo71uqFtE73LbT6b4S95VRgM+dAsr62gLIPHlijHisnMsrOX5bC3+Cxigt7nogGDogMpk3DD5Vi2XJaPKeXUpURUEnQiq++qPKFeaUFphfMRj88DRFIkScoy0VpjrOFisWDdtjRtx3yxIAloq7NMfDKkmFUlFBrNMHw5QJSEColA9tL6Li+oiZgnL21t2xPhfeDk7BhTWCyJsFhyfHxMOrtAFgvK1mMSFMqysoq10rSFIlQKVWuK2mBEM/E1Pjk63xIWWQlIR1DJ5qKBqJwKYigEoLI3Lzntkcf4SW6qD5EUM6E3kosHkUSUlDMQRmMQUoxoBNGaGHJT/tPwzDLjSsC1Led9T0iJxWpB065pXYfzPcl7xHt8nxvn86gvAVnRLjussVS6YDSpGU/G7N65TV3PMMoyni8IwbM6P0e047DWzAQWznN6sWaxWGTZ4VXWmIp9nsyUEtmHS4Nyq0lom8NPUylsqaimmnqs2T2o2dkdo/XpX+0K+YJCm5LR5DbyuMdoQ0gO13f0ztF7T/DZsKF0/pmEdmgR1CEiCsrScuPwFmVpKazh8fERKURKrbIUFjCbzbBFphSdXuR0hk+JorDsHM5olmuSF3TKeaF23SAWJCk0CsJw8auIRkMSzs8uSCRGo5rZbHZZ9Nrik1i3a/7xD/6IyWQCPuLWLUe/+BWp7UidY6QMlbHsVmN0OYJSs7aePnnapqHGYoxQVZayMxijWTZrvAsEW1PbPG5RG4XERCSgBhmDFLPSTFYlcXmCmcn9wNZWyFjThJ6Lfs2iXeZ+dlNRqCJPxXJZa87aEo2+5Ng+Cc+Wc4sJ73qw9jIGFtJgcT0xeFLwJO/xMatwhIGZLsSsxtt7nDg639O0DarSlEpxqDWvliV3U8E0CauUeVNZcDLS9S1t37HuHMFl0m4KV8q/EFEGTCHYkcKWwnRfU40s5chQVJqyVNQjQ1Goz9Ve/13GbDbj7/7dv8fX7j3g/PyMZr3i9PgRi+WCxXLJxWJNOxQAus7jQ26XUZKNnopgC2EynWUJGy2MxhMiAVMKOuqhU8FgjMXaAmtLQoK2zTw6Tcyj/bSikJLg8g3RdytC9IQUqKzFaIPRapi0lCu2WhvG4zFGb7XcngbnHR8+vJeJ+D4QesdyPSf5gMTExApja1Fjw2xvRjWZMikL+hQx0ZNST4iepmtZrBqW6wY3tE/ldU/l7gdt8v0fhJAYcmaXgRVWW5QIMQquz2mO5BLr4Fi7hkjKOn22wpQFdTmiX7useZFU7lP+nO/5zCRe71w2aCkPKlAAMZC8I4Wskx5jnnoUEsPqnlAkfHDE5Ono6XqhbRTjWmGrksOy5rWy4nURpghuE1+mTBTuXEvreta9Q5y+Cns33QYqYa1QTTSjXU0xEqYHitGkYDQusCarEhSFwhbbkPRpmEx3+Dv/yn+Do5NTHj18wMX5Ge//6uccnxxzcnrCo6NjLi7m+JBIaU1MfU7ykpCYQ86UhNFocqnSXNVjIg6xASNZZ81Ym0fF1SM654kCi2ZFiIGYFMoojBhKXdCEntAHVss1aVCLUKIx2mKMznm8EFFaUxSW8XiM0lcTmbb4JFwIPDx+DAz5yxAJziMolCg6ZektjEaG6d4Uu7NPVVQUIaC7jqa5oOsii1XLYt2ybFp8CLmqKblqbqzOi1uMmXYVEzHmqmeOAIXClkiC5CI+BJKPuORoYk8buiw8am1e5OqS8XiKCg3eBbyLubPheRUURIRRaZnUVR6xFSMqeawSqsKQgsEj9C6Srs031SQsMFORCmFHhN1Cs1sIr/Ytsxi57YW3plNujmpUoVm6xEfLjrPOsHKR6Hu863HOI2HgvxBIKvOadg8K9m6MeeX1XcZ7GlsL5RSKUlGUmuR9PsAhoTTbC/8pMFrzyqt3ufnKbb7ylXcJMeC6jqZtWDcNp6cnnJ2d8fOf/5IPP/yQo6MjPvjgQ+aLOednZ6zXa1KK/Pgvfkbf50r6ZDaiGhlmN0rKqqSqS77y7le5e+c1vvSlL/P9H/wp9+7fY/mjP6MsCsqipFt3KGWpRyOUMhhrWKzOMdpS1hWTyQ5FVWAKzXw5Z9213L17C1tYrDGcnV3klMgWn0FVlNy9cYfFasHZxRkhOGIMOZeJovcdTS9cNEv80X3KxTnK1EMxUaFFiFETvEVRU5rAzjg7O8UwWEYrleXj0Zhk6NwwRyGBMVlWfjbdoS5H7E72ct+56zhfnOKT50ACoLFFye2bd9ib7TGb7PD442PWyzXnpxco1OfytJ9ZrFKrfAiIOQGYYpYnMToLV5KEZIckLzlsNQKVwH5h2NGK16xwUBn2S82t2jDSmqlWTEYKVQtHdDzyPY87z0UXWfUR1/W5WBEDMUmWRTFgKkVRa27embJ/c8KtuzvUM0EXYOqEsYKxitD19L1ncdHQrALBb2kCT8QgIW+thWsjCDb0nr29PRaLBePxlJs3b3JycsLt27e5uDjn+PiEi4sLuq6j6zqWiwXL5ZKyKLBWo7VGDzI2ZVkym065fesWO7MZFxdnjEc1xhgKW9DTIwiFtflGMbn3cTN4xAeP+FwNN0YzmYwYj2sQBnqS265gT4E1htsHB1gtrFdLfO8IA/ksSbxkIAQi625NFzyoNntKUQ1dAokoAWMs08mUwlhSCOA8hc15uE3qJ3cwbSTHVSZ7K4UymrIuObx5gPcO7x3jZZVpIwqUtlhTcHBwk1E1pipq5kdLuqbPzs0/g+rzzHpuRoHvW1zfDly2HogYrSiLAmMS1pSkpiX1PSr0VErYs4av7Y95dWT5azPFjbHmYGyoqpqEZh0MKwvHquNXqwXvN46/WDo+WiWWvScuF7i+B+8JZE2oYirs3yrZ2a/45h+8zs7+mL3DMWI8qHx6lM43U7tucd2SRw8WzE97mma7qj8LNgZvNBpx8+YtvvSldwZKiGc+v2CxWHB8fMKjR4+Yz+fcv3+fe/fu8+DBfS7mZwQ6sA2iElrIjHgt7M7GTMYl00nN7VduZJJnTCwvFiiBqrLU5RSA05PH9H1PCD3ziw7RQj2u2T/cZW//BijHcrXi+OgI77aafU/DuKr41rvvcO/xI1aLJb7zuD6QJKd4kiSShqChdSt8N8c7sjZil1hdrFCieO31u+ztztjZuUFdloS+5/zodOAiZrJ1iikPa4q5Yprr3dncxZQoqoLX3rjDqCoprCF4h4gaZt3WaG0pioq+97RNz6OPjlnIMgvhPs8OhRgjXbNGp5hbb9B0rUcNFdJpVZNQOJ85ZsZqglNUea4OGE2wlrOyYq0S933CN54uRi5az2m/ZOEjJ85xEYSTYHL3v4uEzhEIaJvYvzlhNLMc3Dbs36iZ7pa88saMsraUNYSYp/t0Ta7uBZ84frTg9HjJ+z9fsl4EXL/13H4TXG9t2wxmns12qOsROzu73Llz57LxeT5fsFjMOTs/oWmXLJpj2nZFTIHXXnudoih4/71f8dEHH/Do8UNSiPje4XqXvQCVC0ZGZ6URqw1eXJ7G1DtiijTrFWVhmE0njKdjUlCMyhFrv128nobe9zw4ecTF8oJ129I7P1CnFNoK1UQoqoQqe2Yji7a57a5vA82yH/LoAVWtkUojlVBMgZTQVY2PRRYubTraxrFedaRGiD5zUSUN3l+MOV+fHGU5YjKqKIsZWlmMLijKCqUNWlvW65aFXm/cQIrC4oP93DkZz95+5XqCUVhToYxCYoAQkBAobZYn1jrhgiNrawZMjKgUQCui1qxNyUo8IQYWMdF4z2kDjxYNF61nncArizOWPkDwQ9uXzqHodK9i56Dk1msle4c101nFzkGF1ookkeRza4Z3kb4NdG3k9Ljh+HHDyVFHu8rN2Vs8GU+6YDZdAJ9+3abPuK4/O4Vo061yfHLEanXB0ek95otznOu4devW4OHd4+zkhPnFBZih5avPYQdD0UqLQg95HGEg6jqHDw4fPV3bEnygMAXRRgpT0hK2PLenwIfAfDVn3TZ51skwI1ZpyarIVU7riPFU45KytngP7bonJsGuMnNC2R6xHViLriq00tjSEqMhhIRa5EJf13foXhjYt5mpuGl6T4mUPMYIZWmZjccYXWBNhS1LlNYwUH36PlymJcygI/l53rl8tsn86RCRI+CDv+KxfVnwRkrpxoveiZcN23P8xcfvyjl+JuO2xRZbbPHPC7aEry222OILia1x22KLLb6Q2Bq3LbbY4guJl8a4ichrIvKfishPRORHIvI/edH7tMXzh4i8LyI/FJE/FZF/+qL3Z4vni5fpPn5pCgoi8grwSkrp+yIyBf4E+G+mlH78gndti+cIEXkf+G5K6fhF78sWzx8v03380nhuKaUHKaXvD78vgJ8Ad1/sXm2xxRbPgpfpPn5pjNt1iMibwLeBP3rBu7LF80cC/iMR+RMR+R+86J3Z4reHF30fv3SiVyIyAf4fwP80pTR/0fuzxXPHfymldF9EbgL/sYj8NKX0/3vRO7XF88XLcB+/VJ6biFjyAfl3Ukr/7oveny2eP1JK94efj4H/J/C9F7tHWzxvvCz38Utj3CQ3NP7bwE9SSv/rF70/Wzx/iMh4SDIjImPgXwH+4sXu1RbPEy/TffwyVUv/JvCfAT8kt9gC/C9SSv/+i9urLZ4nRORtsrcGOSXyf00p/S9f4C5t8ZzxMt3HL41x22KLLbZ4nnhpwtIttthii+eJrXHbYostvpDYGrctttjiC4mtcdtiiy2+kNgaty222OILia1x22KLLb6Q2Bq3LbbY4guJ/z9tM4XLonMxSgAAAABJRU5ErkJggg==",
+      "text/plain": [
+       "<Figure size 432x288 with 9 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "def split_data(data, labels, split=0.9):\n",
+    "    # shuffle\n",
+    "    index = np.arange(len(data))\n",
+    "    np.random.shuffle(index)\n",
+    "    data = data[index]\n",
+    "    labels = labels[index]\n",
+    "    \n",
+    "    # split\n",
+    "    split = int(len(data)*split)\n",
+    "    data_train = data[:split]\n",
+    "    labels_train = labels[:split]\n",
+    "    data_test = data[split:]\n",
+    "    labels_test = labels[split:]\n",
+    "    \n",
+    "    return data_train, labels_train, data_test, labels_test\n",
+    "\n",
+    "# Affiche les 9 dernières images du jeu de données d'entrainement pour vérifier le bon fonctionnement de la fonction split_data\n",
+    "data_train, labels_train, data_test, labels_test = split_data(data,labels)\n",
+    "fig, axes = plt.subplots(3, 3)\n",
+    "fig.subplots_adjust(hspace=0.6, wspace=0.3)\n",
+    "for i, ax in enumerate(axes.flat):\n",
+    "    ax.imshow(data_train[-i].reshape(3, 32, 32).transpose([1, 2, 0]))\n",
+    "    ax.set_xticks([])\n",
+    "    ax.set_yticks([])\n",
+    "    ax.set_xlabel(labels_train[-i])\n",
+    "    \n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# k-nearest neighbors"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## distance_matrix"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[[2.82842712 2.        ]\n",
+      " [5.65685425 7.21110255]]\n"
+     ]
+    }
+   ],
+   "source": [
+    "def distance_matrix(X, Y):\n",
+    "    \"\"\"function to get the distance matrix between two sets\"\"\"\n",
+    "    x2 = np.sum(X**2, axis=1, keepdims=True)\n",
+    "    y2 = np.sum(Y**2, axis=1, keepdims=True)\n",
+    "    \n",
+    "    return np.sqrt(-2*X.dot(Y.T) + x2  + y2.T)\n",
+    "\n",
+    "# Test distance_matrix function\n",
+    "a = np.array([[1,4], \n",
+    "              [-1,-2]])\n",
+    "b = np.array([[3,2], \n",
+    "              [3,4]])\n",
+    "\n",
+    "print(distance_matrix(a,b))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## knn_predict"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def knn_predict(dists, labels_train, k):\n",
+    "    # Trie les distances\n",
+    "    index = np.argsort(dists)\n",
+    "\n",
+    "    # Sélectionne les k plus proches\n",
+    "    k_nearest = index[:,:k]\n",
+    "\n",
+    "    # Trie les labels correspondant aux k plus proches\n",
+    "    k_nearest_labels = labels_train[k_nearest]\n",
+    "    \n",
+    "    # Cherche le label le plus fréquent parmis les k plus proches\n",
+    "    labels = np.zeros(len(dists), dtype=np.int64)\n",
+    "    for i in range(len(dists)):\n",
+    "        labels[i] = np.argmax(np.bincount(k_nearest_labels[i]))\n",
+    "    \n",
+    "    return labels"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## evaluate_knn"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def evaluate_knn(data_train, labels_train, data_test, labels_test, k):\n",
+    "    # matrice des distances\n",
+    "    dists = distance_matrix(data_test, data_train)\n",
+    "    \n",
+    "    # Prédit les labels\n",
+    "    knn_predict_labels = knn_predict(dists, labels_train, k)\n",
+    "\n",
+    "    # Calcul de précision\n",
+    "    accuracy = np.mean(knn_predict_labels==labels_test)\n",
+    "\n",
+    "    return accuracy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.3576666666666667\n",
+      "0.31316666666666665\n",
+      "0.33616666666666667\n"
+     ]
+    }
+   ],
+   "source": [
+    "accuracy_list = []\n",
+    "\n",
+    "for k in range(1,21):\n",
+    "    accuracy = evaluate_knn(data_train, labels_train, data_test, labels_test, k)\n",
+    "    accuracy_list.append(accuracy)\n",
+    "    print(f\"accuracy for {k}: {accuracy}\")\n",
+    "\n",
+    "plt.plot(np.arange(1,21), accuracy_list)\n",
+    "plt.xlabel(\"k\")\n",
+    "plt.ylabel(\"accuracy\")\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Artificial Neural Network"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Code donné"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.07835058097847951\n"
+     ]
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "\n",
+    "N = 30  # number of input data\n",
+    "d_in = 3  # input dimension\n",
+    "d_h = 3  # number of neurons in the hidden layer\n",
+    "d_out = 2  # output dimension (number of neurons of the output layer)\n",
+    "\n",
+    "# Random initialization of the network weights and biaises\n",
+    "w1 = 2 * np.random.rand(d_in, d_h) - 1  # first layer weights\n",
+    "b1 = np.zeros((1, d_h))  # first layer biaises\n",
+    "w2 = 2 * np.random.rand(d_h, d_out) - 1  # second layer weights\n",
+    "b2 = np.zeros((1, d_out))  # second layer biaises\n",
+    "\n",
+    "data = np.random.rand(N, d_in)  # create a random data\n",
+    "targets = np.random.rand(N, d_out)  # create a random targets\n",
+    "\n",
+    "# Forward pass\n",
+    "a0 = data # the data are the input of the first layer\n",
+    "z1 = np.matmul(a0, w1) + b1  # input of the hidden layer\n",
+    "a1 = 1 / (1 + np.exp(-z1))  # output of the hidden layer (sigmoid activation function)\n",
+    "z2 = np.matmul(a1, w2) + b2  # input of the output layer\n",
+    "a2 = 1 / (1 + np.exp(-z2))  # output of the output layer (sigmoid activation function)\n",
+    "predictions = a2  # the predicted values are the outputs of the output layer\n",
+    "\n",
+    "# Compute loss (MSE)\n",
+    "loss = np.mean(np.square(predictions - targets))\n",
+    "print(loss)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## learn_once_mse"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def learn_once_mse(w1, b1, w2, b2, data, targets, learning_rate):\n",
+    "    \"\"\" Function returning the updated weights and biased after one learning step and the loss \"\"\"\n",
+    "    # Forward pass\n",
+    "    a0 = data  # the data are the input of the first layer \n",
+    "    z1 = np.matmul(a0,w1)+b1  # input of the hidden layer\n",
+    "    a1 = 1/(1+np.exp(-z1))  # output of the hidden layer (sigmoid activation function)\n",
+    "    z2 = np.matmul(a1,w2)+b2  # input of the output layer\n",
+    "    a2 = 1/(1+np.exp(-z2))  # output of the output layer (sigmoid activation function)\n",
+    "    predictions = a2  # the predicted values are the outputs of the output layer\n",
+    "    \n",
+    "    #Compute loss (MSE)\n",
+    "    loss = np.mean(np.square(predictions-targets))\n",
+    "    #Backward pass\n",
+    "    #Compute gradients according to the formula calculated\n",
+    "    grad_a2 = 2*(predictions-targets)\n",
+    "    grad_z2 = grad_a2*a2*(1-a2) \n",
+    "    grad_w2 = np.matmul(a1.T,grad_z2) \n",
+    "    grad_b2 = np.sum(grad_z2,axis=0) \n",
+    "    grad_a1 = np.matmul(grad_z2,w2.T)\n",
+    "    grad_z1 = grad_a1*a1*(1-a1) \n",
+    "    grad_w1 = np.matmul(a0.T,grad_z1) \n",
+    "    grad_b1 = np.sum(grad_z1,axis=0) \n",
+    "\n",
+    "    #Update weights and biaises\n",
+    "    w1 = w1-learning_rate*grad_w1\n",
+    "    w2 = w2-learning_rate*grad_w2\n",
+    "    b1 = b1-learning_rate*grad_b1\n",
+    "    b2 = b2-learning_rate*grad_b2\n",
+    "\n",
+    "    return w1, b1, w2, b2, loss"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### one_hot"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def one_hot(labels):\n",
+    "    if type(labels)==np.int64:\n",
+    "        labels=np.array([labels])\n",
+    "    res=np.zeros((len(labels),9+1))\n",
+    "    res[np.arange(len(labels)),labels]=1\n",
+    "    return res"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### learn_once_cross_entropy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import scipy.special as sp\n",
+    "\n",
+    "def learn_once_cross_entropy(w1, b1, w2, b2, data, targets, learning_rate, batch_size):\n",
+    "    a0 = data  # the data are the input of the first layer \n",
+    "    z1 = np.matmul(a0,w1)+b1  # input of the hidden layer\n",
+    "    a1 = 1/(1+np.exp(-z1))  # output of the hidden layer (sigmoid activation function)\n",
+    "    z2 = np.matmul(a1,w2)+b2  # input of the output layer\n",
+    "    a2 = sp.softmax(z2,axis=1)  # output of the output layer (sigmoid activation function)\n",
+    "    predictions = a2  # the predicted values are the outputs of the output layer\n",
+    "\n",
+    "    # Compute loss (MSE)\n",
+    "    predi = a2.argmax(axis=1)\n",
+    "    c = 0\n",
+    "    for i in range (len(predi)):\n",
+    "        if predi[i] == targets[i]:\n",
+    "            c+=1\n",
+    "    targets = one_hot(targets)\n",
+    "    \n",
+    "    loss=-np.sum(targets*np.log(predictions+1e-8))/batch_size\n",
+    "    grad_z2 = (predictions-targets)/batch_size\n",
+    "    grad_w2 = np.matmul(a1.T,grad_z2) \n",
+    "    grad_b2 = np.sum(grad_z2,axis=0)\n",
+    "    grad_a1 = np.matmul(grad_z2,w2.T) \n",
+    "    grad_z1 = grad_a1*a1*(1-a1)\n",
+    "    a0 = a0.reshape(-1,batch_size)  #reshape data because a0 was (batch_size,) and we wanted (batch_size,1)\n",
+    "    grad_w1 = np.matmul(a0,grad_z1)\n",
+    "    grad_b1 = np.sum(grad_z1,axis=0)\n",
+    "\n",
+    "    # Update weights and biaises\n",
+    "    w1 = w1-learning_rate*grad_w1\n",
+    "    w2 = w2-learning_rate*grad_w2\n",
+    "    b1 = b1-learning_rate*grad_b1\n",
+    "    b2 = b2-learning_rate*grad_b2\n",
+    "\n",
+    "    return w1,b1,w2,b2,c/len(predi)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### train_mlp"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from tqdm import tqdm\n",
+    "\n",
+    "def train_mlp(w1, b1, w2, b2, data_train, labels_train, learning_rate=0.01, nb_epochs=100, batch_size=1):\n",
+    "    train_accuracies=[]\n",
+    "    for i in range(nb_epochs):\n",
+    "        losses=[]\n",
+    "        for j in tqdm(range(int(len(data_train)/batch_size))):\n",
+    "            w1, b1, w2, b2, loss = learn_once_cross_entropy(w1,b1,w2,b2,data_train[j*batch_size:(j+1)*batch_size],labels_train[j*batch_size:(j+1)*batch_size],learning_rate,batch_size)\n",
+    "            losses.append(loss)\n",
+    "\n",
+    "        if len(data_train) % batch_size != 0:\n",
+    "            w1, b1, w2, b2, loss = learn_once_cross_entropy(w1,b1,w2,b2,data_train[j*batch_size:],labels_train[j*batch_size:],learning_rate,len(data_train)%batch_size)\n",
+    "            losses.append(loss)\n",
+    "\n",
+    "        print(f\"epoch {i} : loss {sum(losses)/len(losses)}\")\n",
+    "\n",
+    "        train_accuracies.append(sum(losses)/len(losses))\n",
+    "\n",
+    "    return w1, b1, w2, b2, train_accuracies"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### test_mlp"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def test_mlp(w1, b1, w2, b2, data_test, labels_test):\n",
+    "    a0 = data_test  # the data are the input of the first layer \n",
+    "    z1 = np.matmul(a0,w1)+b1  # input of the hidden layer\n",
+    "    a1 = 1/(1+np.exp(-z1))  # output of the hidden layer (sigmoid activation function)\n",
+    "    z2 = np.matmul(a1,w2)+b2  # input of the output layer\n",
+    "    a2 = sp.softmax(z2)  # output of the output layer (sigmoid activation function)\n",
+    "    predictions = a2  # the predicted values are the outputs of the output layer\n",
+    "    \n",
+    "    # Compute loss (MSE)\n",
+    "    c = 0\n",
+    "    index_predic = a2.argmax(axis=1)\n",
+    "    for i in range(len(index_predic)):\n",
+    "        if index_predic[i] == labels_test[i]:\n",
+    "            c+=1\n",
+    "    return c/len(index_predic)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### run_mlp_training"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def run_mlp_training(data_train, labels_train, data_test, labels_test, dh, learning_rate=0.1, nb_epochs=100, batch_size=200):\n",
+    "    # Initialization of the network weights and biaises\n",
+    "    w1 = 2*np.random.rand(3072,dh)-1  # first layer weights\n",
+    "    b1 = np.zeros((1,dh))  # first layer biaises\n",
+    "    w2 = 2*np.random.rand(dh,10)-1  # second layer weights\n",
+    "    b2 = np.zeros((1,10))  # second layer biaises\n",
+    "\n",
+    "    # Training\n",
+    "    w1, b1, w2, b2, train_accuracies = train_mlp(w1, b1, w2, b2, data_train, labels_train, learning_rate, nb_epochs, batch_size)\n",
+    "\n",
+    "    # Test\n",
+    "    test_accuracy = test_mlp(w1,b1,w2,b2,data_test,labels_test)\n",
+    "\n",
+    "    print(test_accuracy)\n",
+    "\n",
+    "    return train_accuracies, test_accuracy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'data_train' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[1;32m~\\AppData\\Local\\Temp\\ipykernel_21772\\1710715156.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mtrain_accuracies\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtest_accuracy\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mrun_mlp_training\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata_train\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mlabels_train\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mdata_test\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mlabels_test\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;36m64\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;36m0.1\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;36m100\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;36m100\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      2\u001b[0m \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mplot\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtrain_accuracies\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mlabel\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m\"train\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      3\u001b[0m \u001b[0mtest_accuracies\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[0mtest_accuracy\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtrain_accuracies\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      4\u001b[0m \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mplot\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtest_accuracies\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mlabel\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m\"test\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      5\u001b[0m \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlegend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;31mNameError\u001b[0m: name 'data_train' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "train_accuracies, test_accuracy = run_mlp_training(data_train,labels_train,data_test,labels_test,64,0.1,100,100)\n",
+    "plt.plot(train_accuracies, label=\"train\")\n",
+    "\n",
+    "test_accuracies = [test_accuracy for i in range(len(train_accuracies))]\n",
+    "plt.plot(test_accuracies, label=\"test\")\n",
+    "\n",
+    "plt.legend()\n",
+    "plt.show()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000000000000000000000000000000000000..296d654528b719e554528b956c4bf5a1516e812c
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1 @@
+numpy
\ No newline at end of file
diff --git a/results/knn.png b/results/knn.png
new file mode 100644
index 0000000000000000000000000000000000000000..586c6bbdcd7c00f27302bff2d9b2662683266f95
Binary files /dev/null and b/results/knn.png differ
diff --git a/results/mlp.png b/results/mlp.png
new file mode 100644
index 0000000000000000000000000000000000000000..0ed927fff8f058b2aac75462c03a30109ba4312f
Binary files /dev/null and b/results/mlp.png differ