Home▸Machine Learning & Neural Networks▸Perceptron Mistake Bound: Margin, Radius and Novikoff Convergence on Separable Data

Perceptron Mistake Bound: Margin, Radius and Novikoff Convergence on Separable Data

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.

Machine Learning & Neural Networks3DModerate60 FPS📱 Mobile-adapted🟠 Blender⇄ 2D version
Perceptron Mistake Bound: Margin, Radius and Novikoff Convergence on Separable Data ↗ 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

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.

Neural NetworksBackpropagationDeep LearningPerceptronNeural NetworkNovikoff TheoremMarginLinear Classifier

3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install

What did you find?

Add reproduction steps (optional)