Update readme

README.md

@@ -15,21 +15,7 @@ For the entire datasets (5 train batches and 1 test batch), we have the followin
 Each batch is unpickled. All batches are concatenated into a matrix data and a list labels. They are then suffled and split to create training and test datasets.
 
 ### k-nearest neighbours
+We develop a knn model to predict the image labels.
 
-
-### Features
-
-### Background
-
-## Installation
-
-## Requirements
-
-## 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.
-
-## Author
-Sophie BESSAC
-
-## License
-For open source projects, say how it is licensed.
+### mlp
+We use the binary cross entropy to train our model.

mlp.py

@@ -142,6 +142,7 @@ def learn_once_cross_entropy(w1, b1, w2, b2, data, labels_train, learning_rate):
     # Forward pass
     a0 = data # the data are the input of the first layer
     z1 = np.matmul(a0, w1) + b1 # input of the hidden layer
+    z1 = np.clip(z1, -1000, 1000)
     a1 = 1 / (1 + np.exp(-z1)) # output of the hidden layer (sigmoid activation function)
     z2 = np.matmul(a1, w2) + b2 # input of the output layer
     a2 = np.exp(z2) / np.sum(np.exp(z2), axis=1, keepdims=True) # output of the output layer (softmax activation function)
@@ -230,6 +231,7 @@ def train_mlp(w1, b1, w2, b2, data_train, labels_train, learning_rate, num_epoch
         # Forward pass
         a0 = data_train # the data are the input of the first layer
         z1 = np.matmul(a0, w1) + b1 # input of the hidden layer
+        z1 = np.clip(z1, -1000, 1000)
         a1 = 1 / (1 + np.exp(-z1)) # output of the hidden layer (sigmoid activation function)
         z2 = np.matmul(a1, w2) + b2 # input of the output layer
         a2 = np.exp(z2) / np.sum(np.exp(z2), axis=1, keepdims=True) # output of the output layer (softmax activation function)
@@ -267,6 +269,7 @@ def test_mlp(w1, b1, w2, b2, data_test, labels_test):
     # Forward pass
     a0 = data_test # the data are the input of the first layer
     z1 = np.matmul(a0, w1) + b1 # input of the hidden layer
+    z1 = np.clip(z1, -1000, 1000)
     a1 = 1 / (1 + np.exp(-z1)) # output of the hidden layer (sigmoid activation function)
     z2 = np.matmul(a1, w2) + b2 # input of the output layer
     a2 = 1 / (1 + np.exp(-z2)) # output of the output layer (sigmoid activation function)