Constant-time neural decoders for some BCH codes

Author

Tseng, Yuen-Hsien ; Wu, Ja-Ling

Author_Institution

Dept. of Comput. Sci. & Inf. Eng., Nat. Taiwan Univ., Taipei, Taiwan

fYear

1994

fDate

27 Jun-1 Jul 1994

Firstpage

343

Abstract

High-order neural networks (HONN) are shown to decode some BCH codes in constant-time with very low hardware complexity. HONN is a direct extension of the linear perceptron: it uses a polynomial consisting of a set of product terms as its discriminant function. Because a product term is isomorphic to a parity function and a two-layer perceptron for the parity function has been shown by Rumelhart, Hinton, and Williams (1986), HONN has a simple realization if it is considered as having a set of parity networks in the first-half layer, followed by a linear perceptron in the second-half layer. The main problem in using high-order neural networks for a specific application is to decide a proper set of product terms. We apply genetic algorithms to this structure-adaptation problem

Keywords

BCH codes; decoding; error correction codes; error detection codes; feedforward neural nets; genetic algorithms; multilayer perceptrons; polynomials; BCH codes; constant-time neural decoders; discriminant function; error correction codes; error detection codes; genetic algorithms; high-order neural networks; linear perceptron; low hardware complexity; parity function; parity networks; polynomial; product terms; structure-adaptation problem; two-layer perceptron; Computer science; Decoding; Genetic algorithms; Genetic mutations; Hardware; Machine learning; Multilayer perceptrons; Neural networks; Performance analysis; Polynomials;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Theory, 1994. Proceedings., 1994 IEEE International Symposium on

Conference_Location

Trondheim

Print_ISBN

0-7803-2015-8

Type

conf

DOI

10.1109/ISIT.1994.394675

Filename

394675