Perceptron Update

Problem

Apply one perceptron update.

If y * (w dot x) <= 0 the point is misclassified, so return w + lr * y * x elementwise. Otherwise return w unchanged.

Hint

Only update on a mistake; a prediction exactly on the boundary counts as a mistake.

case 1

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

expected: [0.5,1]

case 2

in: [[1,1],[1,1],1,0.1]

expected: [1,1]

case 3

in: [[0.5,-0.5],[1,1],-1,0.2]

expected: [0.3,-0.7]

case 4

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

expected: [1,2]

Starter codePython

def perceptron_update(w, x, y, lr):
    # Your code here
    pass

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