Course Details

Subject {L-T-P / C} : EE3404 : Artificial Neural Network and Fuzzy Logic {3-0-0 / 3}
Subject Nature : Theory
Coordinator : Prof. Ananyo Sengupta


Artificial Neural Network: Characteristics and Benefits of Artificial Neural Network Basic models of Artificial Neurons Basic Activation Functions Network Architectures Adaptive Linear Model: Widro-Hopf solution Classification by single perceptron Training single perceptron by Gauss-Newton method. Multilayer Perceptron: Back-propagation Learning Algorithm Radial Basis Function (RBF) Neural Network, training of RBF Neural Network using stochastic gradient approach, Principal Component Analysis.

Fuzzy Logic: Introduction to crisp sets and fuzzy sets, basic fuzzy set operation and approximate reasoning. Introduction to fuzzy logic modeling and control. Fuzzification, inferencing and defuzzification. Fuzzy knowledge and rule bases. Fuzzy modeling and control schemes for nonlinear systems. Self-organizing fuzzy logic control.

Course Objectives

  1. To learn structure, training methods and applications of artificial neural networks.
  2. To design fuzzy controllers/fuzzy rule based systems

Course Outcomes

At the end of the course, students will be able to
1. Solve the input-output mapping and classification problems using single and multi-layer Perceptron
2. Understand dimension reduction techniques using PCA
3. Design fuzzy rule base and fuzzy controller.

Essential Reading

  1. S. Haykin, Neural Networks: A Comprehensive Foundation, Pearson
  2. T. J. Ross, Fuzzy Logic with Engineering Application, John Wiley and Sons

Supplementary Reading

  1. Konar, Computational Intelligence: Principles, Techniques and Applications, Spinger
  2. V. Kecman, Learning & Soft Computing, Pearson