Skip to main content

IE 702: Neural Nets, Fuzzy Systems and Applications

Prerequisite:  Instructor's permission
 
Contents

Relevance and importance of neural nets, fuzzy systems and combination of such systems in certain problem areas of IE & OR, involving combinatorial optimization, systems modeling, approximations, prediction, robust control and learning.

Artificial neurons; network architectures; learning processes; single and multilayer perceptions; back propagation learning; radial basis function networks; Hopfield models, bi-directional associative memories and combinatorial optimization; Boltzmann machines; Mean Field theory; temporal processing using feed forward networks; dynamically driven recurrent networks; principal components analysis; self-organizing maps; ART type models; Neuro-dynamic programming and reinforcement learning.

Fuzzy sets; fuzzy rules and fuzzy reasoning; temporal fuzzy logic; fuzzy systems; fuzzy associative memories; fuzzy rule generation using neural net approaches; fuzzy inference systems; fuzzy neural networks; adaptive neuro-fuzzy inference systems (ANFIS); neuro-fuzzy control. 
 
References

  • S. Haykin , (1999), 'Neural Networks: A comprehensive foundation,' 2nd Ed., Pearson Education Asia.
  • B. Kosko , (1994), 'Neural Networks and Fuzzy Systems: A dynamical systems approach to machine intelligence,' Prentice Hall India.
  • S.Y. Kung , (1993), 'Digital Neural Networks,' Prentice Hall India.
  • G.J. Klir and B. Yuan, (1997), 'Fuzzy Sets and Fuzzy Logic,' Prentice Hall India.
  • J.S.R.Jang, C. T. Sun and E. Mizutani, ( 1997), 'Neuro-Fuzzy and Soft Computing,' Prentice Hall India.
  • J. Nie and D. Linkens, (1998), 'Fuzzy Neural Control: Principles, algorithms and applications,' Prentice Hall India.
  • S.V. Kartalopoulas (2000), 'Understanding Neural networks and Fuzzy Logic,' IEEE Press and Prentice Hall India.