Thinking Required

TL;DR

This paper reviews the concept of a universal learning algorithm that starts with innate circuits and learns all complex mental functions, aiming to explain the principles behind intelligent behavior.

Contribution

It identifies and discusses the key architectural and functional components necessary for a single general-purpose learning algorithm.

Findings

Lists ingredients of a universal learning algorithm

Highlights the role of innate circuits in learning

Provides a framework for understanding mental algorithms

Abstract

There exists a theory of a single general-purpose learning algorithm which could explain the principles its operation. It assumes the initial rough architecture, a small library of simple innate circuits which are prewired at birth. and proposes that all significant mental algorithms are learned. Given current understanding and observations, this paper reviews and lists the ingredients of such an algorithm from architectural and functional perspectives.