Abstract
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.
References
7
Referenced
55
10.1126/science.165.3891.349
10.1086/406830
10.1073/pnas.79.8.2554
{'key': 'p_13', 'first-page': '461', 'volume': '4', 'author': 'Kitano H.', 'year': '1990', 'journal-title': 'Complex Systems'}
/ Complex Systems by Kitano H. (1990)10.1007/BFb0057623
10.1007/BF02478116
10.1038/ng0498-345
Dates
Type | When |
---|---|
Created | 23 years, 1 month ago (July 27, 2002, 7:55 a.m.) |
Deposited | 4 years, 5 months ago (March 12, 2021, 4:31 p.m.) |
Indexed | 11 months, 1 week ago (Sept. 22, 2024, 11:39 p.m.) |
Issued | 25 years, 2 months ago (July 1, 2000) |
Published | 25 years, 2 months ago (July 1, 2000) |
Published Print | 25 years, 2 months ago (July 1, 2000) |
@article{Astor_2000, title={A Developmental Model for the Evolution of Artificial Neural Networks}, volume={6}, ISSN={1530-9185}, url={http://dx.doi.org/10.1162/106454600568834}, DOI={10.1162/106454600568834}, number={3}, journal={Artificial Life}, publisher={MIT Press - Journals}, author={Astor, J. C. and Adami, C.}, year={2000}, month=jul, pages={189–218} }