Evolution of Neural Net Architectures by a Hierarchical Grammar-Based Genetic Systems

Jacob C, Rehder J (1993)

Publication Language: English

Publication Type: Conference contribution, Original article

Publication year: 1993

Publisher: Springer

City/Town: Wien

Pages Range: 72-79

Conference Proceedings Title: Artificial Neural Nets and Genetic Algorithms - Proceedings of the International Conference (ICANNGA'93)

Event location: Innsbruck AT

ISBN: 978-3-211-82459-7

URI: http://www2.informatik.uni-erlangen.de/publication/download/ANNGA93.1.ps.gz

DOI: 10.1007/978-3-7091-7533-0_12

Abstract

We present a hierarchically structured system for the evolution of connectionist systems. Our approach is exemplified by evolution paradigms for neural network topologies and weights. Our descriptions of a network’s connectivity are based on context-free grammars which are used to characterize signal flow from input to output neurons. Evolution of a simple control task gives a first impression about the capabilities of this approach.

How to cite

APA:

Jacob, C., & Rehder, J. (1993). Evolution of Neural Net Architectures by a Hierarchical Grammar-Based Genetic Systems. In Albrecht, Rudolf F. ; Reeves, C. R. ; Steele, Nigel C. (Eds.), Artificial Neural Nets and Genetic Algorithms - Proceedings of the International Conference (ICANNGA'93) (pp. 72-79). Innsbruck, AT: Wien: Springer.

MLA:

Jacob, Christian, and Jan Rehder. "Evolution of Neural Net Architectures by a Hierarchical Grammar-Based Genetic Systems." Proceedings of the 1st International Conference on Artificial Neural Nets and Genetic Algorithms (ICANNGA'93), Innsbruck Ed. Albrecht, Rudolf F. ; Reeves, C. R. ; Steele, Nigel C., Wien: Springer, 1993. 72-79.

BibTeX: Download