Statistical convergence analysis of Rosenblatt´s perceptron algorithm as a DS-spread spectrum detector

Author

Engel, I. ; Bershad, Neil J.

Author_Institution

RAFAEL, Haifa

Volume

45

Issue

11

fYear

1997

fDate

11/1/1997 12:00:00 AM

Firstpage

2843

Lastpage

2846

Abstract

A stochastic analysis is presented for the learning behavior of a single-layer perceptron when used as a direct sequence (DS) spread spectrum detector. The input is a noisy DS-spread spectrum BPSK signal, the training data is a binary sequence, and the perceptron weights learn using Rosenblatt´s (1962) algorithm

Keywords

binary sequences; convergence of numerical methods; learning (artificial intelligence); noise; perceptrons; phase shift keying; pseudonoise codes; signal detection; spread spectrum communication; statistical analysis; telecommunication computing; DS-spread spectrum detector; Rosenblatt´s perceptron algorithm; binary sequence; direct sequence spread spectrum; learning behavior; noisy DS spread spectrum BPSK signal; perceptron weights; single layer perceptron; statistical convergence analysis; training data; Algorithm design and analysis; Base stations; Binary phase shift keying; Binary sequences; Convergence; Detectors; Signal processing algorithms; Spread spectrum communication; Stochastic processes; Training data;

fLanguage

English

Journal_Title

Signal Processing, IEEE Transactions on

Publisher

ieee

ISSN

1053-587X

Type

jour

DOI

10.1109/78.650110

Filename

650110