Exercise

Training a neural network

Given the fully connected neural network (called model) which you built in the previous exercise and a train loader called train_loader containing the MNIST dataset (which we created for you), you're to train the net in order to predict the classes of digits. You will use the Adam optimizer to optimize the network, and considering that this is a classification problem you are going to use cross entropy as loss function.

Instructions

100 XP

Instantiate the Adam optimizer with learning rate 3e-4 and instantiate Cross-Entropy as loss function.
Complete a forward pass on the neural network using the input data.
Using backpropagation, compute the gradients of the weights, and then change the weights using the Adam optimizer.