Semi batch learning with store management using enhanced conjugate gradient

V. S. Asirvadam*, Huzaifa T A Izzeldin, Nordin Saad, Sean F. Mcloone

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper explores the performance of sliding-window based training, termed as semi batch, using multilayer perceptron (MLP) neural network in the presence of correlated data. The sliding window training is a form of higher order instantaneous learning strategy without the need of covariance matrix, usually employed for modeling and tracking purposes. Sliding-window framework is implemented to combine the robustness of offline learning algorithms with the ability to track online the underlying process of a function. This paper adopted sliding window training with recent advances in conjugate gradient direction with application of data store management e.g. simple distance measure, angle evaluation and the novel prediction error test. The simulation results show the best convergence performance is gained by using store management techniques.

Original languageEnglish
Title of host publicationLecture Notes in Electrical Engineering
Pages61-67
Number of pages7
Volume136 LNEE
DOIs
Publication statusPublished - 25 Jan 2012
Event2nd International Conference of Electrical and Electronics Engineering, ICEEE 2011 - Macau, Macao
Duration: 01 Dec 201102 Dec 2011

Publication series

NameLecture Notes in Electrical Engineering
Volume136 LNEE
ISSN (Print)18761100
ISSN (Electronic)18761119

Conference

Conference2nd International Conference of Electrical and Electronics Engineering, ICEEE 2011
CountryMacao
CityMacau
Period01/12/201102/12/2011

Keywords

  • back-propagation
  • conjugate gradient
  • data store management
  • multilayer perceptron
  • sliding-window learning

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Fingerprint Dive into the research topics of 'Semi batch learning with store management using enhanced conjugate gradient'. Together they form a unique fingerprint.

  • Cite this

    Asirvadam, V. S., Izzeldin, H. T. A., Saad, N., & Mcloone, S. F. (2012). Semi batch learning with store management using enhanced conjugate gradient. In Lecture Notes in Electrical Engineering (Vol. 136 LNEE, pp. 61-67). (Lecture Notes in Electrical Engineering; Vol. 136 LNEE). https://doi.org/10.1007/978-3-642-26001-8_9