perceptron Algorithm

In machine learning, the perceptron is an algorithm for supervised learning of binary classifiers. It is a type of linear classifier, i.e. a categorization algorithm that makes its predictions based on a linear predictor function combine a set of weights with the feature vector. This caused the field of neural network research to stagnate for many years, before it was recognised that a feedforward neural network with two or more layers (also named a multilayer perceptron) had greater processing power than perceptrons with one layer (also named a individual layer perceptron).

Guarantees were given for the Perceptron algorithm in the general non-separable case first by Freund and Schapire (1998), and more recently by Mohri and Rostamizadeh (2013) who extend previous outcomes and give new L1 boundary. The perceptron algorithm was invented in 1958 at the Cornell Aeronautical Laboratory by Frank Rosenblatt, funded by the unite state Office of Naval research.

perceptron source code, pseudocode and analysis