Abstract
This paper considers the role of the embryological algorithm or embryology in defining artificial neural network architecture. Such an approach is based on the biology and growth of the embryonic nervous system and operates by ‘growing’ the neural network from a simple to a complex form. The operation of both the embryology and the genetic algorithm are considered, contrasted and compared. A practical algorithm is presented, together with results demonstrating the relevance, application and advantages of the algorithm.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
R. Dawkins. The Blind Watchmaker. Penguin, 1991.
H. de Garis. Neurite networks: The genetic programming of cellular automata based neural nets which grow. In Proc. IJCNN93, pages 2921–2924. IEEE Press, 1993.
D.E. Goldberg. Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley, Reading, MA, 1989.
A.N. Kolmogorov. On the representation of continuous functions of many variables by superposition of continuous functions of variable and addition. American Math. Soc. Trans., 28:55–59, 1963.
J.D. Schaffer, D. Whitley, and L.J. Eshelman. Combinations of genetic algorithms and neural networks: A survey of the state of the art. In Proc. COGANN-92. IEEE Press, 1992.
F.J. Vico and F. Sandoval. Use of genetic algorithms in neural network definition. In Proc. IWANN91, pages 196–203. Springer-Verlag, 1991.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag Wien
About this paper
Cite this paper
MacLeod, C., Maxwell, G. (1998). Using Embryology as an Alternative to Genetic Algorithms for Designing Artificial Neural Network Topologies. In: Artificial Neural Nets and Genetic Algorithms. Springer, Vienna. https://doi.org/10.1007/978-3-7091-6492-1_79
Download citation
DOI: https://doi.org/10.1007/978-3-7091-6492-1_79
Publisher Name: Springer, Vienna
Print ISBN: 978-3-211-83087-1
Online ISBN: 978-3-7091-6492-1
eBook Packages: Springer Book Archive