Keyboard shortcuts

Press or to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

The Perceptron

In the book: Chapter 1 — The First Neuron.

Chapter 1 builds the perceptron: a unit that computes a weighted sum and thresholds it, together with a learning rule that nudges the weights on every mistake. The chapter shows geometrically that it works. This section shows why — culminating in the perceptron convergence theorem, the guarantee the book invokes at the end of the chapter.

NoteThe claim it formalizes
The formal modelA perceptron's decision boundary is a hyperplane; predictions are half-space membership.
The learning ruleEach mistake-driven update provably moves the score of the offending example in the right direction.
Linear separability and XORAND and OR are linearly separable; XOR provably is not.
The convergence theoremOn separable data, the algorithm converges after finitely many updates — Novikoff's theorem, with proof.
Reading the boundWhat the mistake bound actually says, and what it foreshadows.