C.W.K.
Stream
Quiz · 4 questions

🧩 Neurons, Layers, and Forward Passes

From linear maps to output heads

Level 0Curious
0 XP0/73 lessons0/11 achievements
0/120 XP to next level120 XP to go0% complete

Quiz

01Why do you need a non-linear activation between every two linear layers?
02Which of these is the RIGHT default for the output of a multi-class classifier in PyTorch?
Hint
Read the docstring of CrossEntropyLoss — it tells you exactly what input it expects.
03What is the safest mental model for the relationship between width and depth?
04What is the shape of nn.Linear(in_features=20, out_features=5)'s weight tensor in PyTorch's convention?
Hint
Inspect linear.weight.shape in a REPL and confirm.
Spotted a bug or have feedback on this page?Report an Issue

Comments 0

🔔 Reply notifications (sign in)
Sign inPlease sign in to comment.

No comments yet — be the first.