# Demo entry 6345700

**XOR**

Submitted by **anonymous**
on Feb 02, 2017 at 20:15

Language: Python. Code size: 709 Bytes.

from operator import add # Original XOR points x = [ [0,0], [0,1], [1,0], [1,1] ] y = [ -1, 1, 1, -1 ] w = [0, 0, 0, 0] # Remapping to new feature space with (x_0)(x_1) and 1-(x_0)(x_1) x = [ [x[0], x[1], x[0]*x[1], 1-x[0]*x[1]] for x in x ] # Prediction function def predict(x_i, w): total = sum([x_*w_ for (x_, w_) in zip(x_i ,w)]) return 1 if total > 0 else -1 # Learning while True: cost = 0 for i in range(len(x)): y_ = predict(x[i], w) # Cost is total number of wrong examples # Adding y * x_i to w if misclassified if y_ <> y[i]: cost += 1 w = map(add, w, [y[i] * x_i for x_i in x[i]]) if cost == 0: break print('XOR solved')

This snippet took 0.00 seconds to highlight.

Back to the Entry List or Home.