Abstract
The paper describes a methodology for constructing transfer functions for the hidden layer of a back-propagation network, which is based on evolutionary programming. The method allows the construction of almost any mathematical form. It is tested using four benchmark classification problems from the well-known machine intelligence problems repository maintained by the University of California, Irvine. It was found that functions other than the commonly used sigmoidal function could perform well when used as hidden layer transfer functions. Three of the four problems showed improved test results when these evolved functions were used.
Similar content being viewed by others
References
Minsky M, Papert S (1969) Perceptrons. MIT Press, Cambridge, MA
Rumelhart DE, Hinton GE and Williams RJ (1986) Learning internal representations by error propagation. In: Rumelhart DE, McClelland L (eds) Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: Foundations, MIT Press, Cambridge, MA
Koza JR, Rice JP (1991) Genetic generation of both the weights and architecture for a neural network. In: Proceedings of the International Joint Conference on Neural Networks, Seattle, WA, July 1991
Friedrich CM, Moraga C (1996) An evolutionary method to find good nuilding-blocks for architectures of artificial neural networks. In: Proceedings of the Sixth International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems, Granada, Spain, 1–6 July 1996
Hussain TS, Browse RA (1998) Network generating attribute grammar encoding. In: Proceedings of the IEEE International Joint Conference on Neural Networks, Anchorage, AK, 5–9 May 1998
Pujol JCF, Poli R (1998) Evolving neural networks using a dual representation with a combined crossover operator. In: IEEE International Conference on Evolutionary Computation, Anchorage, AK, 5–9 May 1998
Pujol JCF, Poli R (1998) Evolving the topology and the weights of neural networks using a dual representation. Appl Intellig J 8(1):73–84
Pujol JCF, Poli R (1998) Efficient evolution of asymmetric recurrent neural networks using a PDGP—inspired two-dimensional representation. In: Proceedings of the First European Workshop on Genetic Programming (EuroGP ‘98), Paris, France, April 1998
Poli R (1997) Discovery of symbolic, neuro-symbolic, and neural networks with parallel distributed genetic programming. In: Proceedings of the Third International Conference on Artificial Neural Networks and Genetic Algorithms (ICANNGA ‘97), Norwich, UK, April 1997
Blake CL, Merz CJ (1998) UCI repository of machine learning databases. Irvine, CA: University of California Department of Information and Computer Science, 1998
Koza JR, Bennett III FH, Andre D and Keane MA (1999) The design of analog circuits by means of genetic programming. In: Bentley PJ (ed) Evolutionary design by computers, Wiley, London, UK
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Augusteijn, M.F., Harrington, T.P. Evolving transfer functions for artificial neural networks. Neural Comput & Applic 13, 38–46 (2004). https://doi.org/10.1007/s00521-003-0393-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-003-0393-9