Electrical & Computer Engineering Faculty Publications
Document Type
Article
Publication Date
1-1-1991
Abstract
The authors describe a special type of dynamic neural network called the recursive neural network (RNN). The RNN is a single-input single-output nonlinear dynamical system with a nonrecursive subnet and two recursive subnets arranged in the configuration shown. The authors describe the architecture of the RNN, present a learning algorithm for the network, and provide some examples of its use.
Publisher
IEEE
Publication Title
Proceedings of the 1991 IEEE Workshop Neural Networks for Signal Processing [1991]
ISSN
0-7803-0118-8
First Page
523
Last Page
532
DOI
10.1109/NNSP.1991.239489
Language (ISO)
English
Sponsorship
IEEE
Keywords
Multilayer perceptrons, Neural networks, Nonlinear control systems
Recommended Citation
Abdallah, Chaouki T.; Don Hush; and B. Horne. "Recursive neural networks for signal processing and control." Proceedings of the 1991 IEEE Workshop Neural Networks for Signal Processing [1991] (1991): 523-532. doi:10.1109/NNSP.1991.239489.
