DocumentCode
2017633
Title
An investigation of the properties of evolving fuzzy neural networks
Author
Watts, Michael
Author_Institution
Dept. of Inf. Sci., Otago Univ., Dunedin, New Zealand
Volume
1
fYear
1999
fDate
1999
Firstpage
217
Abstract
The paper presents an investigation into the properties of evolving fuzzy neural networks. It is shown that for the task of isolated phoneme recognition these networks are resistant to forgetting, highly adaptive and possess good generalisation capabilities. It is also shown which training parameters are most relevant to the behaviour of the network, and what effect adjustment of these parameters will have
Keywords
adaptive systems; fuzzy neural nets; generalisation (artificial intelligence); learning (artificial intelligence); speech recognition; adaptive neural network; evolving fuzzy neural networks; generalisation; isolated phoneme recognition; training parameters; Artificial neural networks; Fuzzy logic; Fuzzy neural networks; Fuzzy systems; Immune system; Information science; Input variables; Neural networks; Neurons; Robustness;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Information Processing, 1999. Proceedings. ICONIP '99. 6th International Conference on
Conference_Location
Perth, WA
Print_ISBN
0-7803-5871-6
Type
conf
DOI
10.1109/ICONIP.1999.843989
Filename
843989
Link To Document