Quarterly (winter, spring, summer, fall)
128 pp. per issue
7 x 10, illustrated
ISSN
1064-5462
E-ISSN
1530-9185
2014 Impact factor:
1.39

Artificial Life

Spring 1997, Vol. 3, No. 2, Pages 67-80.
(doi: 10.1162/artl.1997.3.2.67)
© 1997 Massachusetts Institute of Technology
Abstract Genetic Representation of Dynamical Neural Networks Using Kauffman Networks
Article PDF (1.84 MB)
Abstract

Abstract (developmental) genetic representations are schemes where each genotype encodes a program for the construction of a phenotype. A new method for contriving abstract genetic representations is presented, based upon Kauffman's ideas regarding biological development [13-16]. Phenogenesis is controlled by genotype via cell replication and differentiation. Comparison is made with the earlier published methods of Gruau [9] and Kitano [18]. It is argued that greater expressive power is obtained using Kauffman networks. The new method was tested in the artificial evolution of morphology and finally successfully applied to the synthesis of structure in dynamical neural networks.