| 31st October 2020 08:30 AM | |
| Rajkumar Agarwal | Sathyabama Institute of Science and Technology B.E. - Electrical and Electronics Engineering Part Time SECA3026 Fundamentals of Fuzzy Logic and Neura Sathyabama Institute of Science and Technology B.E. - Electrical and Electronics Engineering Part Time SECA3026 Fundamentals of Fuzzy Logic and Neural Networks Syllabus SATHYABAMA INSTITUTE OF SCIENCE AND TECHNOLOGY SCHOOL OF ELECTRICAL AND ELECTRONICS ENGINEERING SECA3026 FUNDAMENTALS OF FUZZY LOGIC AND NEURAL NETWORKS L T P Credits Total Marks 3 0 0 3 100 UNIT 1 FUNDAMENTALS OF ANN 9 Hrs. Introduction - Biological Neuron structure, ANN - Definition – Topology - Models - Learning strategies. Characteristics of ANN - Different Learning Rules - Activation dynamics - Synaptic dynamics - Perceptron Model (Both Single & Multi-Layer) - Training Algorithm - Linear Separability Limitation and Its Over Comings, Problems in perceptron weight adjustments. UNIT 2 MULTI LAYER NETWORKS 9 Hrs. BPN - Training - Architecture-Algorithm, Counter Propagation Network - Training - Architecture, BAM - Training-stability analysis, Adaptive Resonance Theory - ART1- ART2 – Architecture -Training, Hop Field Network - Energy Function - Discrete - Continuous - Algorithm - Application – TSP. UNIT 3 SOM & SPECIAL NETWORKS 9 Hrs. SOM-Introduction - Kohonan SOM - Linear vector quantization, Probabilistic neural network ,Cascade correlation, General Regression neural network, Cognitron - Application of ANN - Texture classification - Character recognition. UNIT 4 INTRODUCTION TO FUZZY LOGIC 9 Hrs. Classical set - Operations and properties - Fuzzy Set - Operations and properties - Problems, Classical Relations - Operations and Properties, Fuzzy Relations - Operations and Properties - Compositions Membership function -FLCS - Need for FLC- Fuzzification - Defuzzification. UNIT 5 FLCS, CLASSIFICATION AND APPLICATIONS 9 Hrs. Fuzzy decision making -Types, Fuzzy Rule Based System, Knowledge Based System, Non linear Fuzzy Control system - Fuzzy Classification - Hard C Means - Fuzzy C Means. Applications of fuzzy - Water level controller, Fuzzy image Classification, Speed control of motor. Max. 45 Hrs. COURSE OUTCOMES On completion of the course, student will be able to CO1 - Classify various topologies of artificial neural networks. CO2 - Illustrate training and learning of neural systems using supervised and unsupervised methodologies. CO3 - Demonstrate the usage of multi-layer and special networks for different case studies. CO4 - Describe the behavior of Fuzzy Logic control system. CO5 - Explain the Defuzzification, fuzzy decision systems. CO6 - Implement Fuzzy based controller for motor speed control, image processing etc. TEXT / REFERENCE BOOKS 1. Timothy Ross, “Fuzzy Logic with Engineering Application”, McGraw Hill, 1997. 2. James A. Freeman & Skapura, “Neural Networks”, Pearson Education, 2007. 3. B.Yegnanarayana, “Artificial Neural Networks” Prentice Hall, September 2007. 4. Simon Haykin, “Artificial Neural Networks”, 2nd Edition, Pearson Education. 5. Drainkov, H.Hallendoor and M.Reinfrank, “An Introduction to Fuzzy Control”, 2001. END SEMESTER EXAMINATION QUESTION PAPER PATTERN Max. Marks: 100 Exam Duration: 3 Hrs. PART A: 10 Questions of 2 marks each-No choice 20 Marks PART B: 2 Questions from each unit with internal choice; each carrying 16 marks 80 Marks |
