Function approximation and time series prediction with neural networks
- 1 January 1990
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 649-665 vol.1
- https://doi.org/10.1109/ijcnn.1990.137644
Abstract
Neural networks are examined in the context of function approximation and the related field of time series prediction. A natural extension of radial basis nets is introduced. It is found that use of an adaptable gradient and normalized basis functions can significantly reduce the amount of data necessary to train the net while maintaining the speed advantage of a net that is linear in the weights. The local nature of the network permits the use of simple learning algorithms with short memories of earlier training data. In particular, it is shown that a one-dimensional Newton method is quite fast and reasonably accurateKeywords
This publication has 5 references indexed in Scilit:
- Fast Learning in Networks of Locally-Tuned Processing UnitsNeural Computation, 1989
- Nonlinear prediction of chaotic time seriesPhysica D: Nonlinear Phenomena, 1989
- The truck backer-upper: an example of self-learning in neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Predicting chaotic time seriesPhysical Review Letters, 1987
- Oscillation and Chaos in Physiological Control SystemsScience, 1977