An upper bound on the performance of a novel feedforward perceptron equalizer

Author

Pulford, Graham W. ; Kennedy, Rodney A. ; Anderson, Brian D O

Author_Institution

Dept. of Electr. & Electron. Eng., Melbourne Univ., Parkville, Vic., Australia

Volume

39

Issue

6

fYear

1993

fDate

11/1/1993 12:00:00 AM

Firstpage

1923

Lastpage

1929

Abstract

The emulation of a nonadaptive, binary, decision-feedback equalizer, operating on a noiseless, finite impulse response channel, by a feedforward multilayer processor is considered. This feedforward perceptron equalizer comprises a triangular array of bandlimiting processing elements. The functional similarity between the two systems is exploited to obtain a tight upper bound on the probability of error as a function of the number of layers, using the theory of finite-state Markov processes

Keywords

Markov processes; equalisers; error statistics; feedback; feedforward neural nets; probability; signal processing; telecommunication channels; bandlimiting processing elements; error probability; feedforward multilayer processor; feedforward perceptron equalizer; finite-state Markov processes; noiseless finite impulse response channel; nonadaptive binary equalizer; performance; triangular array; upper bound; Acoustical engineering; Decision feedback equalizers; Error probability; Feedforward neural networks; Markov processes; Multi-layer neural network; Multilayer perceptrons; Neural networks; Nonhomogeneous media; Upper bound;

fLanguage

English

Journal_Title

Information Theory, IEEE Transactions on

Publisher

ieee

ISSN

0018-9448

Type

jour

DOI

10.1109/18.265500

Filename

265500