Development and Evolution of Neural Networks in an Artificial Chemistry

TL;DR

This paper introduces a decentralized model for artificial neural network development inspired by biological nervous systems, utilizing artificial chemistry and genetic algorithms to evolve complex neural structures.

Contribution

It presents a novel biologically inspired framework for neural network growth and evolution using artificial chemistry and distributed genetic algorithms.

Findings

The model successfully grows networks performing classical conditioning.

Distributed genetic algorithms enable evolution of complex neural structures.

The approach is platform-independent and accessible via the web.

Abstract

We present a model of decentralized growth for Artificial Neural Networks (ANNs) inspired by the development and the physiology of real nervous systems. In this model, each individual artificial neuron is an autonomous unit whose behavior is determined only by the genetic information it harbors and local concentrations of substrates modeled by a simple artificial chemistry. Gene expression is manifested as axon and dendrite growth, cell division and differentiation, substrate production and cell stimulation. We demonstrate the model's power with a hand-written genome that leads to the growth of a simple network which performs classical conditioning. To evolve more complex structures, we implemented a platform-independent, asynchronous, distributed Genetic Algorithm (GA) that allows users to participate in evolutionary experiments via the World Wide Web.