Course Details
Subject {L-T-P / C} : CS6416 : Soft Computing { 3-0-0 / 3}
Subject Nature : Theory
Coordinator : Prof. Anup Nandy
Syllabus
Overview of Soft Computing, Difference between Soft and Hard computing, Brief descriptions of different components of soft computing including Artificial intelligence systems Neural networks, fuzzy logic, genetic algorithms. Artificial neural networks Vs Biological neural networks, ANN architecture, Basic building block of an artificial neuron, Activation functions, Introduction to Early ANN architectures (basics only)-McCulloch & Pitts model, Perceptron, ADALINE, MADALINE [10 Hrs].
Artificial Neural Networks: Supervised Learning: Introduction and how brain works, Neuron as a simple computing element, The perceptron, Backpropagation networks: architecture, multilayer perceptron, backpropagation learning-input layer, accelerated learning in multilayer perceptron, The Hopfield network, Bidirectional associative memories (BAM), RBF Neural Network. [10 Hrs]
Artificial Neural Networks: Unsupervised Learning: Hebbian Learning, Generalized Hebbian learning algorithm, Competitive learning, Self- Organizing Computational Maps: Kohonen Network.
Fuzzy Logic Crisp & fuzzy sets fuzzy relations fuzzy conditional statements fuzzy rules fuzzy algorithm. Fuzzy logic controller. [8]
Genetic algorithms basic concepts, encoding, fitness function, reproduction-Roulette wheel, Boltzmann, tournament, rank, and steady state selections, Convergence of GA, Applications of GA case studies. Introduction to genetic programming- basic concepts. [8]
Course Objectives
- Understand Soft Computing concepts, technologies, and applications
- Understand the underlying principle of soft computing with its usage in various application. .
- Understand different soft computing tools to solve real life problems.
Course Outcomes
Upon successful completion of this course students should be able to: <br />1. Develop application on different soft computing techniques like Fuzzy, GA and Neural network <br />2. Implement Neuro-Fuzzy and Neuro-Fuzz-GA expert system.
Essential Reading
- R. Rajasekaran and G. A and Vijayalakshmi Pa, Neural Networks, Fuzzy Logic, and Genetic Algorithms: Synthesis and Applications, Prentice Hall of India
- D. E. Goldberg, Genetic Algorithms in Search, Optimisation, and Machine Learning, Addison-Wesley
Supplementary Reading
- . L. Fausett, Fundamentals of Neural Networks, Prentice Hall
- T. Ross, Fuzzy Logic with Engineering Applications, Tata McGraw Hill