Access the full text.
Sign up today, get DeepDyve free for 14 days.
Loading next page...
/lp/springer-journals/evolving-transfer-functions-for-artificial-neural-networks-DaxD6i9Ryz
References (11)
-
Carlos Pujol, Riccardo PoliAbstract (1998)
Evolving neural networks using a dual representation with a combined crossover operator1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98TH8360)
-
J. Pujol, R. Poli (1998)
Efficient Evolution of Asymmetric Recurrent Neural Networks Using a PDGP-inspired Two-Dimensional Representation -
T. Hussain, R. Browse (1998)
Network generating attribute grammar encoding1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227), 1
-
J. Pujol, R. Poli (2004)
Evolving the Topology and the Weights of Neural Networks Using a Dual RepresentationApplied Intelligence, 8
-
J. Koza, James Rice (1991)
Genetic generation of both the weights and architecture for a neural networkIJCNN-91-Seattle International Joint Conference on Neural Networks, ii
-
R. Poli (1997)
Discovery of Symbolic, Neuro-Symbolic and Neural Networks with Parallel Distributed Genetic Programming -
D. Rumelhart, James McClelland (1986)
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations -
C. Friedrich, C. Moraga (1996)
An Evolutionary Method to Find Good Building-Blocks for Architectures of Artificial Neural Networks -
J. Koza, D. Andre, M. Keane (2004)
The Design of Analog Circuits by Means of Genetic Programming -
D. Rumelhart, Geoffrey Hinton, Ronald Williams (1986)
Learning internal representations by error propagation -
Catherine Blake (1998)
UCI Repository of machine learning databases
- Publisher
- Springer Journals
- Copyright
- Copyright © 2003 by Springer-Verlag London Limited
- Subject
- ComputerScience
- ISSN
- 0941-0643
- eISSN
- 1433-3058
- DOI
- 10.1007/s00521-003-0393-9
- Publisher site
- See Article on Publisher Site
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.
Journal
Neural Computing and Applications – Springer Journals
Published: Dec 20, 2003