MLP Forward Pass

Problem

Forward pass of a 2-layer MLP with ReLU hidden activation and linear output.

z1 = W1 @ x + b1 (shape: hidden) a1 = relu(z1) z2 = W2 @ a1 + b2 (shape: output)

Return z2 (the output layer pre-activation).

W1 is shape (hidden, input), W2 is shape (output, hidden).

Hint

Two matrix-vector products and a ReLU. Output is linear (no activation).

case 1

in: [[1],[[0.5],[-0.5]],[0,0],[[1,1]],[0]]

expected: [0.5]

case 2

in: [[1,2],[[1,0],[0,1]],[0,0],[[1,1]],[0]]

expected: [3]

case 3

in: [[2,-1],[[1,1],[1,-1]],[0,0],[[2,0],[0,1]],[0,0]]

expected: [2,3]

Starter codePython

def mlp_forward(x, W1, b1, W2, b2):
    # Your code here
    pass

3 test cases · run your code against them in the editor