Skip to main navigation Skip to search Skip to main content

Training of a ML neural network for classification via recursive reduction of the class separation

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

A method for recursive training of a ML network for classification is proposed. It searches for the nonlinear discriminant functions corresponding to several small local minima of the objective function. The novelty of the proposed method lies in the transformation of the training data into new data with a deflated minimum of the objective function followed by iteration to obtain the next solution. It succeeded in finding solutions with lower misclassification errors than the solutions found after conventional training with random initialization of the weights for an OCR application.

Original languageEnglish
Title of host publicationProceedings - 14th International Conference on Pattern Recognition, ICPR 1998
PublisherInstitute of Electrical and Electronics Engineers
Pages450-452
Number of pages3
ISBN (Print)0818685123, 9780818685125
DOIs
StatePublished - 1 Jan 1998
Event14th International Conference on Pattern Recognition, ICPR 1998 - Brisbane, QLD, Australia
Duration: 16 Aug 1998 → 20 Aug 1998

Publication series

NameProceedings - International Conference on Pattern Recognition
Volume1
ISSN (Print)1051-4651

Conference

Conference14th International Conference on Pattern Recognition, ICPR 1998
Country/TerritoryAustralia
CityBrisbane, QLD
Period16/08/98 → 20/08/98

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Training of a ML neural network for classification via recursive reduction of the class separation'. Together they form a unique fingerprint.

Cite this