See https://pytorch.org/docs/stable/generated/torch.nn.CrossEntropyLoss.html for details. It expects an input of size Nsamples x Nclasses, which is un-normalized logits, and a target, which is y_train_l of size Nsamplesx1. You may also feed it y_train_T of size Nsample x Nclasses. Please see the documentation. Cross entropy loss expects raw unnrormalized scores. Soft-max converts raw unnormalized scores to probabilities, which are used to plot the labels. Use SGD and run 20,000 epochs using a learning rate of 1e-2 to train the neural network code: nn = NeuralNet(Nfeatures,Nclasses,20,20).to(device) sm = N.Softmax(dim=1) # Weight the cross entropy loss to balance the classes Nsamples_per_class = y_train_T.sum(axis=0) Weight = Nsamples_per_class.sum()/Nsamples_per_class loss = torch.nn.CrossEntropyLoss(weight=Weight) learning_rate = 0.01 #YOUR CODE HERE optimizer= optim.SGD(net.parameters(), lr=learning_rate) # define optimizer for epoch in range(20000):          #YOUR CODE HERE     predNN = ??   # Forward pass     error = ??    # find the loss     optimizer.zero_grad()              # clear the gradients     backward.loss()              # Send loss backward     optimizer.step()              # update weights      if(np.mod(epoch,5000)==0):       print("Error =",error.detach().cpu().item())       fig,ax = plt.subplots(1,2,figsize=(12,4))       ax[0].plot(y_train_T[0:40].detach().cpu())       ax[1].plot(sm(predNN[0:40]).detach().cpu())       plt.show() Need help with predNN and error formula

See https://pytorch.org/docs/stable/generated/torch.nn.CrossEntropyLoss.html for details. It expects an input of size Nsamples x Nclasses, which is un-normalized logits, and a target, which is y_train_l of size Nsamplesx1. You may also feed it y_train_T of size Nsample x Nclasses. Please see the documentation.

Cross entropy loss expects raw unnrormalized scores. Soft-max converts raw unnormalized scores to probabilities, which are used to plot the labels.

Use SGD and run 20,000 epochs using a learning rate of 1e-2 to train the neural network

code:

nn = NeuralNet(Nfeatures,Nclasses,20,20).to(device)
sm = N.Softmax(dim=1)

# Weight the cross entropy loss to balance the classes
Nsamples_per_class = y_train_T.sum(axis=0)
Weight = Nsamples_per_class.sum()/Nsamples_per_class
loss = torch.nn.CrossEntropyLoss(weight=Weight)
learning_rate = 0.01
#YOUR CODE HERE
optimizer= optim.SGD(net.parameters(), lr=learning_rate) # define optimizer

for epoch in range(20000):
    
    #YOUR CODE HERE
    predNN = ??   # Forward pass
    error = ??    # find the loss
    optimizer.zero_grad()              # clear the gradients
    backward.loss()              # Send loss backward
    optimizer.step()              # update weights 

    if(np.mod(epoch,5000)==0):
      print("Error =",error.detach().cpu().item())
      fig,ax = plt.subplots(1,2,figsize=(12,4))
      ax[0].plot(y_train_T[0:40].detach().cpu())
      ax[1].plot(sm(predNN[0:40]).detach().cpu())
      plt.show()

Need help with predNN and error formula