Evolving connectionist systems for on-line, knowledge-based learning: Principles and applications
Kasabov, Nikola

View/ Open
Cite this item:
Kasabov, N. (1999). Evolving connectionist systems for on-line, knowledge-based learning: Principles and applications (Information Science Discussion Papers Series No. 99/02). University of Otago. Retrieved from http://hdl.handle.net/10523/1122
Permanent link to OUR Archive version:
http://hdl.handle.net/10523/1122
Abstract:
The paper introduces evolving connectionist systems (ECOS) as an effective approach to building on-line, adaptive intelligent systems. ECOS evolve through incremental, hybrid (supervised/unsupervised), on-line learning. They can accommodate new input data, including new features, new classes, etc. through local element tuning. New connections and new neurons are created during the operation of the system. The ECOS framework is presented and illustrated on a particular type of evolving neural networks---evolving fuzzy neural networks (EFuNNs). EFuNNs can learn spatial-temporal sequences in an adaptive way, through one pass learning. Rules can be inserted and extracted at any time of the system operation. The characteristics of ECOS and EFuNNs are illustrated on several case studies that include: adaptive pattern classification; adaptive, phoneme-based spoken language recognition; adaptive dynamic time-series prediction; intelligent agents.
Date:
1999-03
Publisher:
University of Otago
Pages:
33
Series number:
99/02
Keywords:
evolving connectionist systems; on-line learning; spatial-temporal adaptation; adaptive speech recognition; Evolving Fuzzy Neural Networks
Research Type:
Discussion Paper
Collections
- Knowledge Engineering Laboratory [25]
- Information Science [486]
- Discussion Paper [441]