Parallel distributed processing: practical applications of neural networks in signal processing

Author

Schoonees, JA

Author_Institution

Div. for Microelectron. & Commun. Technol., CSIR, Pretoria, South Africa

fYear

1988

fDate

32318

Firstpage

76

Lastpage

80

Abstract

An introduction to artificial neural network models is presented, along with an overview of their practical application and potential applications in signal processing. Successful neural network implementations are described and their performances are compared to those of more traditional signal processing implementations. The Hopfield net, self-organizing feature maps, and the multilayer perceptron are reviewed. Implementation of neural nets in speech synthesis, speech recognition, target identification, image processing, pattern matching, error-correction coding, and neurocomputing are reported. Several ICs in production are briefly mentioned

Keywords

encoding; identification; neural nets; parallel processing; picture processing; signal processing; speech recognition; speech synthesis; Hopfield net; ICs; error-correction coding; feature maps; image processing; multilayer perceptron; neural networks; neurocomputing; parallel distributed processing; pattern matching; signal processing; speech recognition; speech synthesis; target identification; Artificial neural networks; Distributed processing; Image coding; Image processing; Multilayer perceptrons; Neural networks; Pattern matching; Signal processing; Speech recognition; Speech synthesis;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications and Signal Processing, 1988. Proceedings., COMSIG 88. Southern African Conference on

Conference_Location

Pretoria

Print_ISBN

0-87942-709-4

Type

conf

DOI

10.1109/COMSIG.1988.49306

Filename

49306