Algebraic training of a neural network

Silvia Ferrari, Robert F. Stengel

Research output: Contribution to journalArticle

7 Scopus citations

Abstract

A novel algebraic neural network training technique is developed and demonstrated on two well-known architectures. This approach suggests an innovative, unified framework for analyzing neural approximation properties and for training neural networks in a much simplified way. Various implementations show that this approach presents numerous practical advantages; it provides a trouble-free non-iterative systematic procedure to integrate neural networks in control architectures, and it affords deep insight into neural nonlinear control system design.

Original languageEnglish (US)
Pages (from-to)1605-1610
Number of pages6
JournalProceedings of the American Control Conference
Volume2
DOIs
StatePublished - Jun 2001

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Algebraic training of a neural network'. Together they form a unique fingerprint.

  • Cite this