On-line learning, reasoning, rule extraction and aggregation in locally optimized evolving fuzzy neural networks

Fuzzy neural networks are connectionist systems that facilitate learning fr om data, reasoning over fuzzy rules, rule insertion, rule extraction, and r ule adaptation. The concept of a particular class of fuzzy neural networks, called FuNNs. is further developed in this paper to a new concept of evolv ing neuro-fuzzy systems (EFuNNs), with respective algorithms for learning, aggregation, rule insertion, rule extraction. EFuNNs operate in an on-line mode and learn incrementally through locally tuned elements. They grow as d ata arrive, and regularly shrink through pruning of nodes, or through node aggregation. The aggregation procedure is functionally equivalent to knowle dge abstraction. EFuNNs are several orders of magnitude faster than FuNNs a nd other traditional connectionist models. Their features are illustrated o n a bench-mark data set. EFuNNs are suitable for fast learning of on-line i ncoming data (e.g., financial time series, biological process control), ada ptive learning of speech and video data, incremental learning and knowledge discovery from large databases (e.g., in Bioinformatics), on-line tracing processes over time, life-long learning. The paper includes also a short re view of the most common types of rules used in the knowledge-based neural n etworks. (C) 2001 Elsevier Science B.V. All rights reserved.