Artificial Neural Networks
Author:
Top Cited Papers
- 24 February 2005
- book chapter
- Published by Wiley
Abstract
Artificial neural networks are useful tools that have been applied successfully in a broad range of signal‐processing problems. From a signal‐processing perspective, their ability to adapt continuously to new data allows them to track changes in a signal over time, and their ability to learn from arbitrary, noisy data permits them to solve problems that cannot be handled adequately with some of the conventional statistical techniques. This chapter presents the fundamental principles of neural network modeling and illustrates some of the most commonly used neural network architectures for practical problem solving.Keywords
This publication has 7 references indexed in Scilit:
- Recurrent Neural Networks for Prediction2001
- No free lunch theorems for optimizationIEEE Transactions on Evolutionary Computation, 1997
- Neural Networks for Pattern Recognition1995
- Orthogonal least squares learning algorithm for radial basis function networksIEEE Transactions on Neural Networks, 1991
- Self-Organization and Associative Memory1988
- Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectorsBiological Cybernetics, 1976
- A logical calculus of the ideas immanent in nervous activityBulletin of Mathematical Biology, 1943