Abstract

By combining Kohonen learning and Grossberg learning a new type of mapping neural network is obtained. This counterpropagation network (CPN) functions as a statistically optimal self-programming lookup table. The paper begins with some introductory comments, followed by the definition of the CPN. Then a closed-form formula for the error of the network is developed. The paper concludes with a discussion of CPN variants and comments about CPN convergence and performance. References and a neurocomputing bibliography with a combined total of eighty entries are provided.

© 1987 Optical Society of America

Optoelectronic resonator neural networks

Yuri Owechko
Appl. Opt. 26(23) 5104-5111 (1987)

Learning, invariance, and generalization in high-order neural networks

C. Lee Giles and Tom Maxwell
Appl. Opt. 26(23) 4972-4978 (1987)

Multilayer optical learning networks

Kelvin Wagner and Demetri Psaltis
Appl. Opt. 26(23) 5061-5076 (1987)

Electronic hardware implementations of neural networks

A. P. Thakoor, A. Moopenn, John Lambe, and S. K. Khanna
Appl. Opt. 26(23) 5085-5092 (1987)

Nearest matched filter classification of spatiotemporal patterns

Robert Hecht-Nielsen
Appl. Opt. 26(10) 1892-1899 (1987)