Module-1: [8 Hours]
Fundamental Concepts: Introduction to Artificial Neural Networks (ANN), Models of a Neuron. Network structure Learning Process: Error–correction learning, Hebbian learning, competitive learning, Boltzmann learning, the credit-assignment problem, supervised learning, and other learning techniques.

Module-2: [11 Hours]
Single neuron/ Perceptron networks: Training methodology, typical application to linearly separable problems. Multilayer Perceptron: Back propagation algorithm, virtues and limitation of BP algorithm, modifications to back-propagation.

Module-3: [8 Hours]
Radial-basis function Networks – interpolation problem, Cover’s theorem, Regularization networks, Self-Organizing Maps (SOM), Learning Vector Quantization (LVQ), applications.

Module-4: [6 Hours]
Introduction to Fuzzy systems, Membership function, Fuzzy relational operation, Fuzzy IF THEN rules, Fuzzy Reasoning.

Module-5: [5 Hours]
Sugeno and Mamdani type systems, Adaptive Neuro-Fuzzy systems, training methods, Application of ANN and Fuzzy systems to non-stationary time series prediction pattern classification.

To design and development of soft computing algorithms.

To analyze the real time problem and find solution to the same using soft computing techniques.

1. To understand the fundamental concepts of Soft Computing techniques
2. To study and apply Artificial Neural Networks and different Learning techniques.
3. To understand and apply different Perceptron techniques.
4. To understand and analyse different techniques for data classification.
5. To study and analyse Fuzzy Set theory and its application.

S. Haykin, Neural Networks - A Comprehensive Foundation, Peasrson Education, India

Jang, Sun and Mizutani, Neuro-Fuzzy and Soft-Computing – A computational approach to learning and machine intelligence, Prentice Hall of India

S. Kumar, Neural Networks: A Classroom approach, Tata McGraw Hill

Martin T. Hagan, Howard B. Demuth, Mark H. Beale, Neural Network Design, Thomson