Incremental learning neural network for pattern classification

Cheng An Hung, Sheng-Fuu Lin

Research output: Contribution to journalArticle

2 Scopus citations

Abstract

A neural network architecture that incorporates a supervised mechanism into a fuzzy adaptive Hamming net (FAHN) is presented. The FAHN constructs hyper-rectangles that represent template weights in an unsupervised learning paradigm. Learning in the FAHN consists of creating and adjusting hyper-rectangles in feature space. By aggregating multiple hyper-rectangles into a single class, we can build a classifier, to be henceforth termed as a supervised fuzzy adaptive Hamming net (SFAHN), that discriminates between nonconvex and even discontinuous classes. The SFAHN can operate at a fast-learning rate in online (incremental) or offline (batch) applications, without becoming unstable. The performance of the SFAHN is tested on the Fisher iris data and on an online character recognition problem.

Original languageEnglish
Pages (from-to)913-928
Number of pages16
JournalInternational Journal of Pattern Recognition and Artificial Intelligence
Volume13
Issue number6
DOIs
StatePublished - 1 Jan 1999

Fingerprint Dive into the research topics of 'Incremental learning neural network for pattern classification'. Together they form a unique fingerprint.

  • Cite this