M.Sc. (Information Technology) Soft Computing Techniques Syllabus - Mumbai University 2026

• a Introduction of soft computing - soft computing vs. hard computing, various types of soft computing techniques, Fuzzy Computing, Neural Computing, Genetic Algorithms, Associative Memory, Adaptive Resonance Theory, Classification, Clustering, Bayesian Networks, Probabilistic reasoning, applications of soft computing.
• b Artificial Neural Network - Fundamental concept, Evolution of Neural Networks, Basic Models, McCulloh-Pitts Neuron, Linear Separability, Hebb Network.
• c Supervised Learning Network - Perceptron Networks, Adaptive Linear Neuron, Multiple Adaptive Linear Neurons, Backpropagation Network, Radial Basis Function, Time Delay Network, Functional Link Networks, Tree Neural Network

• a Associative Memory Networks - Training algorithm for pattern Association, Autoassociative memory network, hetroassociative memory network, bi-directional associative memory, Hopfield networks, iterative autoassociative memory networks, temporal associative memory networks. Kohonen self-organizing feature maps, learning vectors quantization, counter propogation networks, adaptive resonance theory networks.
• b Special Networks - Simulated annealing, Boltzman machine, Gaussian Machine, Cauchy Machine, Probabilistic neural net, cascade correlation network, cognition network, neo-cognition network, cellular neural network, optical neural network
• c Third Generation Neural Networks - Spiking Neural networks, convolutional neural networks, deep learning neural networks, extreme learning machine model.
• d UnSupervised Learning Networks - Fixed weight competitive nets

• a Introduction to Fuzzy Logic, Classical Sets and Fuzzy sets - Classical sets, Fuzzy sets.
• b Classical Relations and Fuzzy Relations - Cartesian Product of relation, classical relation, fuzzy relations, tolerance and equivalence relations, non- iterative fuzzy sets.
• c Membership Function - features of the membership functions, fuzzification, methods of membership value assignments.
• d Defuzzification - Lambda-cuts for fuzzy sets, Lambda-cuts for fuzzy relations, Defuzzification methods.
• e Fuzzy Arithmetic and Fuzzy measures - fuzzy arithmetic, fuzzy measures, measures of fuzziness, fuzzy integrals.

• a Fuzzy Rule base and Approximate reasoning - Fuzzy proportion, formation of rules, decomposition of rules, aggregation of fuzzy rules, fuzzy reasoning, fuzzy inference systems, Fuzzy logic control systems, control system design, architecture and operation of FLC system, FLC system models and applications of FLC System.
• b Genetic Algorithm - Biological Background, Traditional optimization and search techniques, genetic algorithm and search space, genetic algorithm vs. traditional algorithms, basic terminologies, simple genetic algorithm, general genetic algorithm, operators in genetic algorithm, stopping condition for genetic algorithm flow, constraints in genetic algorithm, problem solving using genetic algorithm, the schema theorem, classification of genetic algorithm, Holland classifier systems, genetic programming, advantages and limitations and applications of genetic algorithm.Differential Evolution Algorithm, Hybrid soft computing techniques – neuro – fuzzy hybrid, genetic neuro-hybrid systems, genetic fuzzy hybrid and fuzzy genetic hybrid systems.

Books and References

• 1 Artificial Intelligence and Soft Anandita Das SPD 3rd 2018 Computing Battacharya
• 2 Principles of Soft computing S.N.Sivanandam Wiley 3 rd 2019 S.N.Deepa
• 3 Neuro-Fuzzy and Soft J.S.R.Jang, Prentice 2004 Computing C.T.Sun and Hall of India E.Mizutani
• 4 Neural Networks, Fuzzy Logic S.Rajasekaran, G. Prentice 2004 and Genetic Algorithms: A. Vijayalakshami Hall of India Synthesis & Applications
• 5 Fuzzy Logic with Engineering Timothy J.Ross McGraw- 1997 Applications Hill
• 6 Genetic Algorithms: Search, Davis E.Goldberg Addison 1989 Optimization and Machine Wesley Learning
• 7 Introduction to AI and Expert Dan W. Patterson Prentice 2009 System Hall of India