Perceptron

المُدرِك (البرسيبترون)

Definition

The simplest neural network: a single unit that sums its weighted inputs and applies a threshold to give a binary output.

Definition

The perceptron is the simplest neural unit: it computes a weighted sum of inputs and applies a threshold to output a binary decision, trained by an error-correcting rule.

Practical examples

Code example Python
import numpy as np

X = np.array([[0,0],[0,1],[1,0],[1,1]])
y = np.array([0,0,0,1])
w, b = np.zeros(2), 0.0
for _ in range(10):
    for x, t in zip(X, y):
        p = int(w @ x + b > 0)
        w += (t - p) * x
        b += (t - p)
print([int(w @ x + b > 0) for x in X])

Expected output

[0, 0, 0, 1]

Learn and review

Suggested terms to learn next