Card image cap
Deep neural netowrks # 1
In last tutorial series we wrote 2 layers neural networks model, now it's time to build deep neural network, where we could have whatever count of layers we want.
Card image cap
Deep neural netowrks # 2
Now when we have initialized our parameters, we will do the forward propagation module by implementing functions that we'll use when implementing the model.
Card image cap
Deep neural netowrks # 3
Just like with forward propagation, we'll implement helper functions for backpropagation and calculate the gradient of the loss function with respect to the parameters.
Card image cap
Deep neural netowrks # 4
In this part we will implement the backward function for the whole network and we will also update the parameters of the model, using gradient descent.
Card image cap
Deep neural netowrks # 5
In this tutorial we will use the functions we had implemented in the previous parts to build a deep network, and apply it to cat vs dog classification.
Card image cap
Deep neural netowrks # 6
Training neural network requires specifying an initial value of the weights. You'll see that a well chosen initialization method could improve learning and accuracy.