PyTorch Certified Associate Practice Questions - PyTorch Certified Associate (PTCA) Exam

What does calling .backward() on a scalar loss tensor do?

It updates the model weights using the optimizer It computes the gradients of the loss with respect to all leaf tensors that have requires_grad=True It zeroes out all previously accumulated gradients It performs the forward pass through the network

Correct Answer:

It computes the gradients of the loss with respect to all leaf tensors that have requires_grad=True

Access more questions from this quiz

Continue to PyTorch Certified Associate Practice Questions - PyTorch Certified Associate (PTCA) Exam for more practice questions and the full quiz experience.

Access More Questions