LEARN++: An incremental learning algorithm for multilayer perceptron networks

R. Polikar, L. Udpa, S. S. Udpa, V. Honavar

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

26 Scopus citations

Abstract

We introduce a supervised learning algorithm that gives neural network classification algorithms the capability of learning incrementally from new data without forgetting what has been learned in earlier training sessions. Schapire's (1990) boosting algorithm, originally intended for improving the accuracy of weak learners, has been modified to be used in an incremental learning setting. The algorithm is based on generating a number of hypotheses using different distributions of the training data and combining these hypotheses using a weighted majority voting. This scheme allows the classifier previously trained with a training database, to learn from new data when the original data is no longer available, even when new classes are introduced. Initial results on incremental training of multilayer perceptron networks on synthetic as well as real-world data are presented in this paper.

Original languageEnglish (US)
Title of host publicationDesign and Implementation of Signal Processing SystemNeural Networks for Signal Processing Signal Processing EducationOther Emerging Applications of Signal ProcessingSpecial Sessions
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3414-3417
Number of pages4
ISBN (Electronic)0780362934
DOIs
StatePublished - Jan 1 2000
Externally publishedYes
Event25th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2000 - Istanbul, Turkey
Duration: Jun 5 2000Jun 9 2000

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume6
ISSN (Print)1520-6149

Other

Other25th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2000
Country/TerritoryTurkey
CityIstanbul
Period6/5/006/9/00

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'LEARN++: An incremental learning algorithm for multilayer perceptron networks'. Together they form a unique fingerprint.

Cite this