Introductory Session on Soft Computing

Introductory Session on Soft Computing

• 1.
  Motivation towards SoftComputing Adri Jovin J J, M.Tech., Ph.D. UITE221- SOFT COMPUTING
• 2.
  Course Objective The courseis aimed at exposing the students to the concepts of soft computing and its importance in the real-world scenario. This includes an insight on neural networks, fuzzy logic and genetic algorithm. It also helps the students about the hybridization of various soft computing techniques. UITE221 SOFT COMPUTING 2
• 3.
  Prerequisite & LearningApproach Prerequisite : Data Structures Course Credits : 3 Lecture : 3 Course Type : Professional Elective Course History : First time offered / Semester 07 / Academic Year: 2020 - 21 UITE221 SOFT COMPUTING 3
• 4.
  Course Learning Outcomes Afterundergoing the course, students will be able to: 1. Distinguish between supervised and unsupervised learning 2. Develop solutions using neural networks for real world problems which require a supervised learning approach 3. Design applications based on fuzzy logic membership function and fuzzy inference systems 4. Solve single-objective optimization problems using Genetic Algorithm UITE221 SOFT COMPUTING 4
• 5.
  Course Content Introduction Artificial neuralnetwork: Introduction, characteristics- learning methods – taxonomy – Evolution of neural networks- basic models – important terminologies – applications. Fuzzy logic: Introduction – crisp sets- fuzzy sets – crisp relations and fuzzy relations: Cartesian product of relation – classical relation, fuzzy relations, tolerance and equivalence relations, non-iterative fuzzy sets. Genetic algorithm: Introduction – biological background – traditional optimization and search techniques – Genetic basic concepts UITE221 SOFT COMPUTING 5
• 6.
  Course Content Neural Networks McCulloch-Pittsneuron – linear separability – Hebb network – supervised learning network: perceptron networks – adaptive linear neuron, multiple adaptive linear neuron, BPN, RBF, TDNN- associative memory network: auto-associative memory network, hetero-associative memory network, BAM, Hopfield networks, iterative auto-associative memory network & iterative associative memory network – unsupervised learning networks: Kohonen self-organizing feature maps, LVQ – CP networks, ART network UITE221 SOFT COMPUTING 6
• 7.
  Course Content Fuzzy Logic Membershipfunctions: features, fuzzification, methods of membership value assignments- Defuzzification: lambda cuts – methods – fuzzy arithmetic and fuzzy measures: fuzzy arithmetic – extension principle – fuzzy measures – measures of fuzziness -fuzzy integrals – fuzzy rule base and approximate reasoning : truth values and tables, fuzzy propositions, formation of rules-decomposition of rules, aggregation of fuzzy rules, fuzzy reasoning-fuzzy inference systems-overview of fuzzy expert system-fuzzy decision making. UITE221 SOFT COMPUTING 7
• 8.
  Course Content Genetic Algorithm Geneticalgorithm and search space – general genetic algorithm – operators – Generational cycle – stopping condition – constraints – classification genetic programming – multilevel optimization – real life problem- advances in GA. UITE221 SOFT COMPUTING 8
• 9.
  Reference Books 1. S.Rajasekaran and G. A.Vijayalakshmi Pai, “Neural Networks, Fuzzy Logic and Genetic Algorithm: Synthesis & Applications”, Prentice-Hall of India Pvt. Ltd., 2006. ISBN-13: 978-8120353343 2. S. N. Sivanandam and S. N. Deepa, “Principles of Soft Computing”, Wiley India Pvt. Ltd, 2011. ISBN-13: 978- 8126577132 3. David E. Goldberg, “Genetic Algorithm in Search Optimization and Machine Learning” Pearson Education India, 2013. ISBN-13: 978-8177588293 4. George J. Klir, Ute St. Clair, Bo Yuan, “Fuzzy Set Theory: Foundations and Applications” Prentice Hall, 1997. UITE221 SOFT COMPUTING 9
• 10.
  Assessment Content Weightage Nos.Marks Test 12.5 2 25 Quiz 1 5 5 Assignment 5 2 10 Total 40 UITE221 SOFT COMPUTING 10