دالة الخطوة والقرارات الخطية

The weighted sum gives a score, but you often need a clean yes or no. A step function turns that raw score into a firm decision.

The step function outputs 1 if the score is at or above zero, and 0 if it is below. No in-between, just on or off. ⚡

Zero is the threshold where the decision flips. Cross it and the neuron fires; stay below and it stays quiet.

Changing the bias slides that threshold. A larger bias makes the neuron fire more easily, a smaller one makes it harder.

With two inputs, the firing rule draws a straight line on a graph. Points on one side say yes, points on the other say no.

That line is the decision boundary. It splits your feature space into two regions, one class on each side.

The weights control the angle and steepness of the boundary. Adjusting them rotates the dividing line across your data.

This is a linear decision: the boundary is always a straight line or flat plane. It cannot bend or curve around the data.

If one straight line can split your classes cleanly, the data is linearly separable. A single neuron handles this case perfectly.

The step's hard edge jumps abruptly from 0 to 1. That sharp jump has no useful slope, which makes gradient-based learning tricky later.

Combine the weighted sum with a step and you have a working binary classifier in two short lines of Python.

Think about the shape a single neuron can carve.

The step function turns a score into 0 or 1 at a threshold. With two inputs it draws a straight decision boundary, splitting linearly separable data. 📏