More Information
Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21
List of All Issues » Issue TOC

Neural Computation

Fall 1991, Vol. 3, No. 3, Pages 375-385
(doi: 10.1162/neco.1991.3.3.375)
© 1991 Massachusetts Institute of Technology
FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling
Article PDF (354.23 KB)
A. D. Back
Department of Electrical Engineering, University of Queensland, Queensland 4072, Australia
A. C. Tsoi
Department of Electrical Engineering, University of Queensland, Queensland 4072, Australia
Abstract

A new neural network architecture involving either local feedforward global feedforward, and/or local recurrent global feedforward structure is proposed. A learning rule minimizing a mean square error criterion is derived. The performance of this algorithm (local recurrent global feedforward architecture) is compared with a local-feedforward global-feedforward architecture. It is shown that the local-recurrent global-feedforward model performs better than the local-feedforward global-feedforward model.