Astor, J. C. and Adami, C. (2000) A Developmental Model for the Evolution of Artificial Neural Networks. Artificial Life, 6 (3). pp. 189-218. ISSN 1064-5462 http://resolver.caltech.edu/CaltechAUTHORS:ASTal00
- Published Version
See Usage Policy.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:ASTal00
We present a model of decentralized growth and development for artificial neural networks (ANNs), inspired by developmental biology and the physiology of 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. The chemicals and substrates, in turn, are modeled by a simple artificial chemistry. While the system is designed to allow for the evolution of complex networks, we demonstrate the power of the artificial chemistry by analyzing engineered (handwritten) genomes that lead to the growth of simple networks with behaviors known from physiology. To evolve more complex structures, a Java-based, platform-independent, asynchronous, distributed genetic algorithm (GA) has been implemented that allows users to participate in evolutionary experiments via the World Wide Web.
|Additional Information:||© 2001 Massachusetts Institute of Technology. This work was supported in part by the NSF under grant PHY-9723972, as well as a fellowship of the Studienstiftung des Deutschen Volkes to J.A.|
|Subject Keywords:||artificial neural network, (distributed) genetic algorithms, neurogenesis, gene expression, artificial chemistry, artificial life, Java|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||MICHELLE ALDECUA|
|Deposited On:||14 Nov 2008 18:34|
|Last Modified:||26 Dec 2012 10:31|
Repository Staff Only: item control page