---
title: "Theory of Self-Organizing Nerve Nets with Special Reference to Association and Concept Formation"
authors:
  - "Shun-ichi Amari"
doi: ""
url: "https://ijcai.org/proceedings/1979/4"
pdf: "https://ijcai.org/proceedings/1979/0004.pdf"
venue: "Proceedings of the Sixth International Joint Conference on Artificial Intelligence"
year: 1979
pages: ""
track: ""
keywords:
---

# Theory of Self-Organizing Nerve Nets with Special Reference to Association and Concept Formation

Shun-ichi Amari

*Proceedings of the Sixth International Joint Conference on Artificial Intelligence*.

## Abstract

The present paper proposes a mathematical the0ry of self-organi~ing nerve.nets, which is applicable to various types of supervised and unsuperv1sed lear~1ng, such as learning decision, concept formation, association, etc. Given an env1ronmentainformation source, a neural system auto~atically forms a number of separate rout1nes to process the signals in it. This kind of unsupervised self-organization underlies commonly in formation of categories, feature extractors. and content addressable . memories. This problem is analyzed mathematically, as well as models of topographlc organization of nerve fields and of associativ~ memories, by the pruposed method.