Home▸Machine Learning & Neural Networks▸Perceptron Mistake Bound: Margin, Radius and Weight Vector Convergence (2D)

Perceptron Mistake Bound: Margin, Radius and Weight Vector Convergence (2D)

The same perceptron model as the 3D scene: a top-down plane of two classes, the true separator with its margin band, the learning perceptron weight vector and separator, and the cosine to the true normal after each update.

Machine Learning & Neural Networks2DModerate60 FPS📱 Mobile-adapted🟠 Blender⇄ 3D version
Perceptron Mistake Bound: Margin, Radius and Weight Vector Convergence (2D) ↗ Open standalone

Train a perceptron on linearly separable points and watch its weight vector turn toward the true separator after every mistake. The Novikoff theorem says the number of mistakes can never exceed (R/gamma)^2, where R is the data radius and gamma the margin. Change the margin, radius, number of points and separator angle, with checks of the proof inequalities, rotation and scaling invariance built in. A Blender-built pegboard.

⚙ Under the hood

The same perceptron model as the 3D scene: a top-down plane of two classes, the true separator with its margin band, the learning perceptron weight vector and separator, and the cosine to the true normal after each update.

PerceptronNeural NetworkNovikoff TheoremMarginLinear Classifier

2D · HTML5 Canvas 2D · 60 FPS target · runs fully client-side, no install

What did you find?

Add reproduction steps (optional)