Abstract
A neural network, combining evolution and learning is introduced. The novel feature of the proposed network is the evolutionary character of its neurons. The argument of the transfer function performed by the neurons in the network is neither a linear nor polynomial function of the inputs to the neuron, but an unknown general function P(·). The adequate functional form P(·) for each neuron, is achieved during the learning period by means of genetic programming. The proposed neural network is applied to the problem domain of time series prediction of the Mackey-Glass delay differential equation. Simulation results indicate that the new neural network is effective.
Similar content being viewed by others
References
Angeline, P. J., Sauders, G. M. and Pollak, J. B.: An evolutionary algorithm to constructs recurrent neural networks. IEEE Transactions on Neural Networks, 5 (1994), 54–65.
Chalmers, D. J.: The Evolution of Learning: An Experiment in Genetic Connectionism. In: Proceedings on the 1990 Connectionist Models Summer School, 1990. Morgan Kauffmann, San Mateo, CA.
Crowder, R. S.: Predicting the Mackey-Glass Time Series with Cascade-Correlation Learning. In: Proceedings on the 1990 Connectionist Models Summer School, 1990. Morgan Kauffmann, San Mateo, CA.
Fontanari, J. F. and Meir, R.: Evolving a learning algorithm for the binary perceptron. Network, 2 (1991), 353–359.
Frean, M.: The upstart algorithm: a method for constructing and training feed-forward neural networks. Neural Computation, 2 (1990), 198–209.
Jang, J. S. R.: ANFIS: Adaptive-network-based fuzzy inference system. IEEE Transactions on Systems, Man and Cybernetics, 23 (1993), 665–685.
Kantz, H., and Schreider, T.: Nonlinear Time Series Analysis. Cambridge University Press, 1997.
Koza, J.R.: Genetic Programming.MIT Press, 1992.
Lee, S. W.: Off-Line Recognition of Totally Unconstrained Hand-Written Numerals Using Multilayer Cluster Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18 (1996), 648–652.
Mackey, M. C.and Glass, L.: oscillation and chaos in physiological control systems. Science, 197 287–289, 1977.
Moody, J. Fast Learning in Multi-Resolution Hierarchies.In: Advances in Neural Information Processing Systems I, 29–39, 1989. Morgan Kaufmann, San Mateo, CA.
Whitley, D., Starkweather, T. and Bogart, C.: Genetic algorithms and neural networks: optimizing connections and connectivity. Parallel Computation, 14 (1990), 347–361.
Yao, X. Evolutionary Artificial Networks. In: Encyclopedia of Computer Science and Technology, 1995. Marcel Dekker, New York.
Yao, X. Evolving artificial neural networks. Proceedings of the IEEE, 87 (1999), 1423–1445.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Alvarez, A. A Neural Network with Evolutionary Neurons. Neural Processing Letters 16, 43–52 (2002). https://doi.org/10.1023/A:1019747726343
Issue Date:
DOI: https://doi.org/10.1023/A:1019747726343