last results of mlp

README.md

@@ -43,32 +43,6 @@ Ces fonctions permettent de calculer la précision de l'algorithme k-NN pour dif
 
 ### Backpropagation in a Neural Network
 
-#### Partial Derivatives with Chain Rule
-
-1. **\(\frac{\partial C}{\partial A^{(2)}}\)**:
-   \(\frac{\partial C}{\partial A^{(2)}} = \frac{2}{N_{out}}(\hat{Y} - Y)\)
-
-2. **\(\frac{\partial C}{\partial Z^{(2)}}\)**:
-   \(\frac{\partial C}{\partial Z^{(2)}} = \frac{2}{N_{out}}(\hat{Y} - Y) \cdot \sigma(Z^{(2)}) \cdot (1 - \sigma(Z^{(2)}))\)
-
-3. **\(\frac{\partial C}{\partial W^{(2)}}\)**:
-   \(\frac{\partial C}{\partial W^{(2)}} = \frac{\partial C}{\partial Z^{(2)}} \cdot A^{(1)T}\)
-
-4. **\(\frac{\partial C}{\partial B^{(2)}}\)**:
-   \(\frac{\partial C}{\partial B^{(2)}} = \frac{\partial C}{\partial Z^{(2)}}\)
-
-5. **\(\frac{\partial C}{\partial A^{(1)}}\)**:
-   \(\frac{\partial C}{\partial A^{(1)}} = (W^{(2)T} \cdot \frac{\partial C}{\partial Z^{(2)}})\)
-
-6. **\(\frac{\partial C}{\partial Z^{(1)}}\)**:
-   \(\frac{\partial C}{\partial Z^{(1)}} = \frac{\partial C}{\partial A^{(1)}} \cdot \sigma'(Z^{(1)})\)
-
-7. **\(\frac{\partial C}{\partial W^{(1)}}\)**:
-   \(\frac{\partial C}{\partial W^{(1)}} = \frac{\partial C}{\partial Z^{(1)}} \cdot A^{(0)T}\)
-
-8. **\(\frac{\partial C}{\partial B^{(1)}}\)**:
-   \(\frac{\partial C}{\partial B^{(1)}} = \frac{\partial C}{\partial Z^{(1)}\)
-
 
 # Neural Network Training and Testing Overview
 

main.py

 from read_cifar import read_cifar, split_dataset
 from knn import evaluate_knn_for_k, plot_accuracy_versus_k
 import matplotlib.pyplot as plt
-from mlp2 import run_mlp_training, plot_accuracy_versus_epoch
+from mlp import run_mlp_training, plot_accuracy_versus_epoch