Introduction to Neural Networks: Biological inspiration, Perceptron and its limitations, Multilayer Perceptron, Training Neural Networks: Backpropagation algorithm, Gradient descent optimization, Overfitting and regularization, Hyper parameter tuning, Kohonen’s Self- Organizing Networks – Hopfield Networks, Boltzmann Machine, Introduction to Advanced Architectures: CNN, RNN and Auto encoders

Introduction to Evolutionary Algorithms: Biological inspiration, Genetic algorithms (GA), Evolution strategies (ES), Genetic programming (GP), Genetic Algorithms: Representation and initialization, Selection, crossover, and mutation, Fitness evaluation, Convergence and diversity maintenance, Advanced Evolutionary Techniques: Differential evolution (DE), Particle swarm optimization (PSO)

Introduction to Fuzzy Logic: Fuzzy sets and membership functions, Fuzzy rules and reasoning, Fuzzy inference systems, Defuzzification methods, Designing Fuzzy Systems: Fuzzy controllers, Fuzzy clustering, Fuzzy decision making, Applications in control systems and data analysis

Hybrid Computational Intelligence Systems: Neuro-fuzzy systems, Genetic-fuzzy systems, Applications and case studies.

Preamble

This course covers the principles and applications of computational intelligence techniques, including artificial neural networks, evolutionary algorithms, and fuzzy systems. Students will gain theoretical knowledge and practical skills to design, implement, and analyze intelligent systems

Course Objectives

• Gain comprehensive knowledge of neural network architectures and training techniques, including backpropagation, gradient descent, and hyperparameter tuning.
• Develop proficiency in designing and implementing genetic algorithms and fuzzy logic systems, with a focus on real-world applications and hybrid computational intelligence systems.

Course Outcomes

Prerequisites

• Basic programming knowledge (Python or MATLAB)
• Introductory courses in linear algebra, calculus, and probability

CO-PO Mapping

CO-PO Mapping

Evaluation Pattern – 70:30

• Midterm Exam – 20%
• Lab Assignments & Case Study – 50%
• End Semester Exam – 30%

Text Book / References

1. C. Eberhart, “Computational Intelligence: Concept to Implementations”, Morgan Kaufmann Publishers, 2007.
2. Timothy J. Ross, “Fuzzy Logic with Engineering Applications,” 4th Edition, Wiley, 2016
3. Laurence Fausett, “Fundamentals of Neural Networks”, Prentice Hall,1994
4. Nazmul Siddique, Hojjat Adeli, “Computational Intelligence: Synergies of Fuzzy Logic, Neural Networks and Evolutionary Computing”, Willey 2013