Performance analysis of a converged single-layer perceptron for nonseparable data models with bias terms

Author

Bershad, Neil J. ; Shynk, John J.

Author_Institution

Dept. of Electr. & Comput. Eng., California Univ., Irvine, CA, USA

Volume

42

Issue

1

fYear

1994

fDate

1/1/1994 12:00:00 AM

Firstpage

175

Lastpage

188

Abstract

Rosenblatt´s (1985) algorithm is a recursive method used to adjust the weights of a single-layer perceptron. It is capable of partitioning the input signal space into two regions that are separated by a hyperplane boundary. Thus, when the values of the input signal are linearly separable, the algorithm will converge to a stable stationary point that yields zero mean-square error. The authors examine the stationary points of Rosenblatt´s algorithm when the data is not linearly separable. A system identification model is used to generate the data. The model incorporates the effects of bias terms so that the hyperplane boundaries do not necessarily pass through the origin of the signal space. An expression is also derived for the probability of an incorrect classification of the output signal when the weights are converged at a stationary point

Keywords

convergence of numerical methods; estimation theory; feedforward neural nets; identification; probability; Rosenblatt´s algorithm; bias terms; converged single-layer perceptron; hyperplane boundary; incorrect classification probability; input signal space partioning; nonseparable data models; performance analysis; recursive method; stable stationary point; system identification model; weights adjustment; zero mean-square error; Convergence; Data models; Multilayer perceptrons; Neural networks; Partitioning algorithms; Performance analysis; Signal generators; Signal processing algorithms; System identification; Vectors;

fLanguage

English

Journal_Title

Signal Processing, IEEE Transactions on

Publisher

ieee

ISSN

1053-587X

Type

jour

DOI

10.1109/78.258132

Filename

258132