This course provides an in-depth exploration of soft computing techniques, including fuzzy logic, neural networks, and optimization methods. Students will learn to understand the complexities of human decision-making and how to apply these principles to solve real-world problems. The course emphasizes both theoretical foundations and practical applications, equipping students with the skills to navigate and implement various soft computing methodologies.
Understand the concepts of fuzzy logic, neural networks, and optimization techniques.
Comprehend the complex nature of human decision-making, incorporating partial truths and past experiences.
Gain familiarity with fuzzy concepts and their operations.
Acquire knowledge of various soft computing techniques used in computations.
Apply fundamental techniques in soft computing to solve real-world problems.
Unit I: Introduction to Neural Networks
Overview of biological neural systems and the history of neural networks.
Mathematical models of neurons and artificial neural network (ANN) architecture.
Learning rules and paradigms: supervised, unsupervised, and reinforcement learning.
Training algorithms: Perceptrons, delta rule, backpropagation, and multilayer perceptron models.
Applications of artificial neural networks, including Hopfield networks and associative memories.
Unit II: Fuzzy Logic Fundamentals
Introduction to fuzzy logic and its significance.
Comparison of classical and fuzzy sets, including membership functions.
Fuzzy rule generation and its applications in decision-making.
Unit III: Operations on Fuzzy Sets
Basic operations: complement, intersection, union, and aggregation of fuzzy sets.
Understanding nonspecificity in fuzzy and crisp sets and the fuzziness of fuzzy sets.
Unit IV: Fuzzy Arithmetic
Introduction to fuzzy numbers and linguistic variables.
Arithmetic operations on fuzzy intervals and numbers.
Fuzzy equations and the lattice of fuzzy numbers.
Unit V: Evolutionary Computing and Neuro-Fuzzy Systems
Overview of evolutionary computing techniques: genetic algorithms, swarm intelligence, and bacterial foraging.
Introduction to neuro-fuzzy systems and their architecture.
Applications of evolutionary techniques and their integration with fuzzy logic.
Anderson, J.A., An Introduction to Neural Networks, PHI, 1995.
Hertz, J., Krogh, R.G., Palmer, R., Introduction to the Theory of Neural Computation, Addison-Wesley, 1991.
Klir, G.J., Yuan, B., Fuzzy Sets & Fuzzy Logic, PHI, 2009.
Mitchell, M., An Introduction to Genetic Algorithms, PHI, 1997.
Kartalopoulos, S.V., Understanding Neural Networks and Fuzzy Logic: Basic Concepts and Applications, IEEE Press – PHI, 1997.
Rajasekaran, S., Pai, G.A.V., Neural Networks, Fuzzy Logic and Genetic Algorithms: Synthesis & Applications, PHI, 2003.
A foundational understanding of programming and basic concepts in mathematics, particularly in set theory and probability.
Lectures, practical labs, group projects, and case studies.