Neural Networks and Fuzzy Logic
4 Periods / Week
Duration of Exam
Basic model of a neuron. Neural network topologies: Feed forwa
rd topology and
Recurrent topology; Neural network activation functions; Neural network learning
algorithms: Supervised learning, Un
supervised learning, Reinforcement learning;
Fundamentals of connectionist modeling: McCulloach
Pits model, Perceptron,
Topology of multi
layer perceptron, Backpropagation learning algorithm,
Applications and limitations of Multi layer perceptron. Classification of Neural
networks; Radial Basis Function networks: Topology, learning algorithm fo
Applications; Kohenen’s self
organising network: Topology, learning algorithm,
Applications; Hopfield network: Topology, learning algorithm, Applications of
Basic concepts of Recurrent neural networks; Dynamics of recu
networks; Architecture and Training algorithms and applications of Recurrent neural
networks; Industrial commercial applications of Neural networks: Semiconductor
manufacturing processes, Communication, Process monitoring and optimal control,
Robotics, Decision fusion and pattern recognition.
Introduction to Fuzzy systems; Fuzzy sets and operations on Fuzzy sets;
Fuzzy relations; Fuzzy measures, Fuzzy integrals, Fuzziness and fuzzy resolution;
possibility theory and Fuzzy
arithmetic; composition and inference; Considerations
of fuzzy decision
Basic structure and operation of Fuzzy logic control systems; Design methodology
and stability analysis of fuzzy control systems; Applications of Fuzzy controllers.
pplications of fuzzy theory.
Fakhreddine O. Karray and Clarence De Silva., “
Soft Computing and
Intelligent Systems Design, Theory, Tools and Applications”,
Education, India, 2009.
Satish Kumar, “
Neural Networks: A Classroom app
McGraw Hill, 2004.
Timothy J. Ross, “
Fuzzy Logic with Engineering Applications
Teng Lin and C.S.George Lee, “
Neural Fuzzy Systems”,