Course Outline:

Part I: Basics - Mathematical preliminaries: Universal approximation of multivariate functions, Nonlinear error surface and optimization principle, Statistical learning theory and classification.
Part II: Neural Networks: Back-propagation network, Radial Basis function network, Recurrent network.
Part III: Fuzzy logic: Primer- Fuzzy set theory, Fuzzy rule base and inference mechanism, Fuzzy neural networks.
Part IV: Genetic Algorithm: Primer, Evolutionary neural networks,
Part V: A project work that involves implementation of soft-computing principle in real-world application.

References/Books

V. Kecman, Learning and Soft Computing, The MIT Press, Cambridge, MA, 2001
T.J.Ross: Fuzzy logic with engineering applications McGraw Hill NY, 1995
K. Deb: Optimization for engineering design, Prentice Hall India, New Delhi, 1995
K.Deb, Multi-objective optimization using evolutionary algorithms, John Wiley & Sons, , NY, 2002.
D.E.Goldberg: Genetic algorithms in search, optimization and machine learning, Addision Wesley, Mass. 1989.
S. Haykin: Neural networks, McMillan College Pub. N.Y., 1994
M.H.Hassoun: Fundamentals of artificial neural networks, Prentice Hall India, New Delhi, 1995

Proposed by: Drs. Brahma Deo (MME), K. Deb (ME), P.K. Kalra, L. Behera (EE), P. Chakraborty (CE)
Prerequisite: ESO 218 computational methods in engineering
Laboratory: Demonstrations will be possible if the number of students remain within a reasonable limit.