Fuzzy inferencing with ART networks

Sunanda Mitra

Research output: Contribution to conferencePaperpeer-review

Abstract

A recent trend in developing adaptive decision models has been to integrate the concept of fuzzy membership functions of data samples with adaptive learning inherent to neural nets. Several different approaches have been suggested for such integration involving Adaptive Resonance Theory as well as Kohonen self-organizing neural networks. Such neuro-fuzzy models appear to be quite effective in successful clustering of complex data samples encountered in many pattern recognition and control applications where traditional decision models fail due to lack of knowledge of data distributions and unavailability of training data sets. The strengths and weaknesses of currently existing ART-based neuro-fuzzy models are described.

Original languageEnglish
Pages1230-1234
Number of pages5
StatePublished - 1994
EventProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA
Duration: Jun 27 1994Jun 29 1994

Conference

ConferenceProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
CityOrlando, FL, USA
Period06/27/9406/29/94

Fingerprint

Dive into the research topics of 'Fuzzy inferencing with ART networks'. Together they form a unique fingerprint.

Cite this