Neural Networks

Perceptron Visualizer

Understand the building block of AI. Visualize how weights and bias define a decision boundary to separate classes.

Weight 1 (x₁): 0.5

Weight 2 (x₂): -0.5

Bias (b): 0.1

x₁

x₂

f(z)

📜 Theory

A **Perceptron** computes a weighted sum of inputs:
z = (w₁ * x₁) + (w₂ * x₂) + b

It then applies a step function:
y = 1 if z ≥ 0, else -1

💡 Goal

Adjust the sliders so that all **Blue** points are in the blue region and **Red** points are in the red region. This is called finding a Linearly Separable solution.