DeepAI AI Chat
Log In Sign Up

Development and Evolution of Neural Networks in an Artificial Chemistry

by   Jens C. Astor, et al.
Hochschule Heilbronn

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.


page 2

page 3

page 7


Modeling the Evolution of Gene-Culture Divergence

We present a model for evolving agents using both genetic and cultural i...

Real-time Evolution of Multicellularity with Artificial Gene Regulation

This paper presents a real-time simulation involving ”protozoan-like” ce...

Forest structure in epigenetic landscapes

Morphogenesis is the biological process that causes the emergence and ch...

Towards Self-Assembling Artificial Neural Networks through Neural Developmental Programs

Biological nervous systems are created in a fundamentally different way ...

Evolution of differentiated expression patterns in digital organisms

We investigate the evolutionary processes behind the development and opt...

Neural networks grown and self-organized by noise

Living neural networks emerge through a process of growth and self-organ...