π©βπ» Python Code Snippets
Last updated
Last updated
A function that computes gradients to optimize loss functions using backpropagation
Dividing each row vector of x by its norm.
A normalizing function used when the algorithm needs to classify two or more classes
The loss is used to evaluate the performance of the model. The bigger the loss is, the more different that predictions ( yΜ ) are from the true values ( y ). In deep learning, we use optimization algorithms like Gradient Descent to train the model and to minimize the cos
The loss is used to evaluate the performance of the model. The bigger the loss is, the more different that predictions ( yΜ ) are from the true values ( y ). In deep learning, we use optimization algorithms like Gradient Descent to train the model and to minimize the cost.
Doing the "forward" and "backward" propagation steps for learning the parameters.
The goal is to learn Ο and b by minimizing the cost function J. For a parameter Ο
Functions of 2-layer NN
Input layer, 1 hidden layer and output layer
Initializing W
s and b
s, W
s must be initialized randomly in order to do symmetry-breaking, we can do zero initalization for b
s
Each layer accepts the input data, processes it as per the activation function and passes to the next layer
The average of the loss functions of the entire training set due to the output layer -from A2 in our example-
Proper tuning of the weights ensures lower error rates, making the model reliable by increasing its generalization.
Updating the parameters due to the learning rate to complete the gradient descent