A NEW STABLE ON-LINE LEARNING ALGORITHM FOR TAKAGI-SUGENO-KANG TYPE NEURO-FUZZY NETWORKS

作者：Topalov Andon Venelinov^*

来源：Comptes Rendus de l Academie Bulgare des Sciences, 2011, 64(10): 1489-1498.

• fuzzy-neural networks
• learning systems
• variable structure systems

A new variable structure systems' theory based on on-line learning algorithm has been developed for training of Takagi-Sugeno-Kang type fuzzy rule-based neural networks. The convergence of the algorithm is established and the conditions are given. Its salient characteristics are stable on-line tuning of the parameters in the premise and the consequence parts of the fuzzy rules and fast learning speed.

• 出版日期2011