Dense Layer Forward & Backward

medium
Unit 9 · Backprop & Regularization0/3 to milestone

Implement the forward and backward pass of a fully connected layer Y=XW+bY = XW + b.

  • forward(X, W, b) → Y
  • backward(X, W, dY) → (dX, dW, db)

Shapes: X (n, d_in), W (d_in, d_out), b (d_out,), dY (n, d_out).

#backprop#neural-networks2 visible + 1 hidden tests
solution.py · Python 3.13
Loading editor…
Run your code to see results. ⌘↵ to run · ⌘⇧↵ to submit
Dense Layer Forward & Backward · TechGradify