Structure

A Course in 2 Chapters:

1. Forward Pass
   • 1 Layer (weights biases) ⭐matrix *
   • Activation Function (ReLU 📈, softmax 📊) ⭐matrix * | + softmax
   • Loss (entropy loss) ⭐matrix * | + softmax | + loss
2. Backward Pass
   • Gradient descent method (Gradients, Chain rule) 
   • Loss gradient, Activation gradient, Layer gradient ⭐training ⭐testing

🌟🌟🌟Sweet treat🌟🌟🌟: our own drawing tool