Tags: Soft Computing Syllabus, ME/M.Tech 2nd semester Syllabus, MCTA 201 Syllabus, ME/M.Tech Second Semester Syllabus, Computer Tech. & Applications M.Tech Syllabus, Software Systems M.Tech Syllabus
Rajiv Gandhi Technological University, Bhopal (MP)
Computer Tech. & Applications (UTD, RGTU, Bpl)
Software Systems SATI (Vidisha)
ME/M.Tech. 1st FIRST SEMESTER SYLLABUS
MCTA 201 Soft Computing Syllabus
Computer Tech. & Applications (UTD, RGTU, Bpl)
Software Systems SATI (Vidisha)
ME/M.Tech. 1st FIRST SEMESTER SYLLABUS
MCTA 201 Soft Computing Syllabus
Unit 1
ARTIFICIAL NEURAL NETWORKS : Basic concepts - Importance of tolerance of imprecision and uncertainty. Biological and artificial neuron, Single layer perception - Multilayer Perception - Supervised and Unsupervised learning – Back propagation networks - Kohnen's self organizing networks - Hopfield network.
Unit 2
FUZZY SYSTEMS : Introduction, History of the Development of Fuzzy Logic, Fuzzy sets and Fuzzy reasoning - Fuzzy matrices - Fuzzy functions - Decomposition - Fuzzy automata and languages - Fuzzy control methods - Fuzzy decision making.
Unit 3
NEURO - FUZZY MODELING : Adaptive networks based Fuzzy interface systems - Classification and Regression Trees - Data clustering algorithms - Rule based structure identification - Neuro-Fuzzy controls - Simulated annealing – Evolutionary computation.
Unit 4
GENETIC ALGORITHMS: Survival of the Fittest - Fitness Computations - Cross over - Mutation - Reproduction - Rank method - Rank space method.
Unit 5
SOFT COMPUTING AND CONVENTIONAL AI : AI search algorithm - Predicate calculus - Rules of interference – Semantic networks - Frames - Objects - Hybrid models – Applications, MATLAB Toolbox - An Overview.
Reference Books:
1. S. Rajasekran, G.A. Vijayalaxmi Pai “Neural Network, Fuzzy Logic and Genatic
Algorithm”.
2. Martin T. Hagan, Howard B. Demuth, Mark Beale “Neural Network Design, VPH
Pub.
3. Bert Kosko “Neural Networks and Fuzzy Systems” PHI Pub.
4. Keeman “Learning & soft computing”, Pearson
5. Philip d. W asserman “Neural Computing”, Van Nastrand Reinhold pub.
ARTIFICIAL NEURAL NETWORKS : Basic concepts - Importance of tolerance of imprecision and uncertainty. Biological and artificial neuron, Single layer perception - Multilayer Perception - Supervised and Unsupervised learning – Back propagation networks - Kohnen's self organizing networks - Hopfield network.
Unit 2
FUZZY SYSTEMS : Introduction, History of the Development of Fuzzy Logic, Fuzzy sets and Fuzzy reasoning - Fuzzy matrices - Fuzzy functions - Decomposition - Fuzzy automata and languages - Fuzzy control methods - Fuzzy decision making.
Unit 3
NEURO - FUZZY MODELING : Adaptive networks based Fuzzy interface systems - Classification and Regression Trees - Data clustering algorithms - Rule based structure identification - Neuro-Fuzzy controls - Simulated annealing – Evolutionary computation.
Unit 4
GENETIC ALGORITHMS: Survival of the Fittest - Fitness Computations - Cross over - Mutation - Reproduction - Rank method - Rank space method.
Unit 5
SOFT COMPUTING AND CONVENTIONAL AI : AI search algorithm - Predicate calculus - Rules of interference – Semantic networks - Frames - Objects - Hybrid models – Applications, MATLAB Toolbox - An Overview.
Reference Books:
1. S. Rajasekran, G.A. Vijayalaxmi Pai “Neural Network, Fuzzy Logic and Genatic
Algorithm”.
2. Martin T. Hagan, Howard B. Demuth, Mark Beale “Neural Network Design, VPH
Pub.
3. Bert Kosko “Neural Networks and Fuzzy Systems” PHI Pub.
4. Keeman “Learning & soft computing”, Pearson
5. Philip d. W asserman “Neural Computing”, Van Nastrand Reinhold pub.
ConversionConversion EmoticonEmoticon