Title :
Evolving connectionist systems: A theory and a case study on adaptive speech recognition
Author_Institution :
Dept. of Inf. Sci., Otago Univ., Dunedin, New Zealand
Abstract :
The paper introduces evolving connectionist systems (ECOS) as an effective approach to building online adaptive intelligent systems. ECOS evolve through incremental, hybrid (supervised/unsupervised), online 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 network (EFuNN). EFuNN 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 EFuNN are illustrated on a case study of adaptive, phoneme-based spoken language recognition
Keywords :
adaptive signal processing; evolutionary computation; fuzzy neural nets; knowledge based systems; learning (artificial intelligence); multilayer perceptrons; speech recognition; ECOS; EFuNN; adaptive speech recognition; evolving connectionist systems; evolving fuzzy neural network; incremental hybrid online learning; one-pass learning; online adaptive intelligent systems; phoneme-based spoken language recognition; spatial-temporal sequence adaptive learning; Adaptive control; Adaptive systems; Computer aided software engineering; Information science; Intelligent structures; Intelligent systems; Neural networks; Neurons; Programmable control; Speech recognition;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.836007
