Robust adaptive learning of feedforward neural networks via LMI optimizations

Xingjian Jing

Research output: Journal article publicationJournal articleAcademic researchpeer-review

34 Citations (Scopus)

Abstract

Feedforward neural networks (FNNs) have been extensively applied to various areas such as control, system identification, function approximation, pattern recognition etc. A novel robust control approach to the learning problems of FNNs is further investigated in this study in order to develop efficient learning algorithms which can be implemented with optimal parameter settings and considering noise effect in the data. To this aim, the learning problem of a FNN is cast into a robust output feedback control problem of a discrete time-varying linear dynamic system. New robust learning algorithms with adaptive learning rate are therefore developed, using linear matrix inequality (LMI) techniques to find the appropriate learning rates and to guarantee the fast and robust convergence. Theoretical analysis and examples are given to illustrate the theoretical results.
Original languageEnglish
Pages (from-to)33-45
Number of pages13
JournalNeural Networks
Volume31
DOIs
Publication statusPublished - 1 Jul 2012

Keywords

  • Feed-forward neural network (FNN)
  • Linear matrix inequality (LMI)
  • Robust control approach
  • Robust learning

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Robust adaptive learning of feedforward neural networks via LMI optimizations'. Together they form a unique fingerprint.

Cite this