Dense Layer Forward

Problem

Compute one dense (fully connected) layer without an activation: y = W @ x + b.

The signature is dense_forward(x, W, b). W has shape (output_dim, input_dim), x has length input_dim and b has length output_dim.

Hint

One dot product per output row of W, then add the bias.

case 1

in: [[1,2],[[1,0],[0,1]],[0.5,-0.5]]

expected: [1.5,1.5]

case 2

in: [[2],[[3]],[1]]

expected: [7]

case 3

in: [[1,-1],[[2,3]],[0]]

expected: [-1]

case 4

in: [[0.5,0.5],[[1,1],[2,2]],[0,0]]

expected: [1,2]

case 5

in: [[1,2,3],[[1,-1,0.5]],[2]]

expected: [2.5]

Starter codePython

def dense_forward(x, W, b):
    # Your code here
    pass

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