Symbolic information in recurrent neural networks: Issues of representation and training
Loading...
Authors
Omlin, Christian W. P.
Issue Date
1994-12
Type
Electronic thesis
Thesis
Thesis
Language
ENG
Keywords
Computer Science
Alternative Title
Abstract
In recent years, there has been a renewed interest in artificial neural networks. The discovery of new learning algorithms has made them promising tools in diverse applications such as pattern recognition, signal processing, knowledge acquisition for expert systems, prediction of protein structures, and dynamical system modeling. Recurrent neural networks which are able to store state information over indefinite time spans are particularly well-suited for modeling dynamical systems such a stock markets, speech, and physical systems.
Description
December 1994
School of Science
School of Science
Full Citation
Publisher
Rensselaer Polytechnic Institute, Troy, NY