Title

Exploiting Regularity Without Development

Abstract

A major challenge in evolutionary computation is to find the right level of abstraction of biological development to capture its essential properties without introducing unnecessary inefficiencies. In this paper, a novel abstraction of natural development, called Compositional Pattern Producing Networks (CPPNs), is proposed. Unlike most computational abstractions of natural development, CPPNs do not include a developmental phase, differentiating them from developmental encodings. Instead of development, CPPNs employ compositions of functions derived from gradient patterns present in developing natural organisms. In this paper, a variant of the NeuroEvolution of Augmenting Topologies (NEAT) method, called CPPN-NEAT, evolves increasingly complex CPPNs, producing patterns with strikingly natural characteristics. Copyright © 2006, American Association for Artificial Intelligence (www.aaai.org). All rights reserved.

Publication Date

12-1-2006

Publication Title

AAAI Fall Symposium - Technical Report

Volume

FS-06-03

Number of Pages

49-56

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

Socpus ID

33947227425 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/33947227425

This document is currently not available here.

Share

COinS