From the perceptron to the cerebellum

TL;DR

This paper reviews the evolution of the perceptron model from its origins in artificial neural networks to its biological applications in cerebellar learning, discussing historical theories and recent advances.

Contribution

It provides a comprehensive overview of the perceptron's role in both artificial intelligence and neuroscience, connecting early theories with current research questions.

Findings

Historical connection between perceptron and cerebellar models

Review of Marr and Albus theories of cerebellar learning

Discussion of recent developments and open questions

Abstract

The perceptron has served as a prototypical neuronal learning machine in the physics community interested in neural networks and artificial intelligence, which included G\'erard Toulouse as one of its prominent figures. It has also been used as a model of Purkinje cells of the cerebellum, a brain structure involved in motor learning, in the early influential theories of David Marr and James Albus. We review these theories, more recent developments in the field, and highlight questions of current interest.