Soft Computing Course : Online Learning Resources & Teaching Materials

1 . Course Type : Soft Computing : Online Learning Resources & Teaching Materials; Full Course Lectures 42 hrs; Slides, notes include text, tables, diagrams, examples, algorithms, pseudo codes and book references, offered free online in 9 PDF files, total 398 Pages. curriculum standard B.Tech, 7th semester, CSE. Students can learn online; Teachers can use/adopt as part of their teaching material. ; 2 . Course Description : Soft Computing : Full Course Lectures 42 hrs; Topics - Introduction to Soft Computing; Fundamentals of Neural Network; Back Propagation Network; Associative Memory; Adaptive Resonance Theory; Fuzzy Set Theory; Fuzzy Systems; Fundamentals of Genetic Algorithms; Hybrid Systems. The course materials are offered free online in PDF files. The contents are more traditional and self explanatory for online learning. Students can learn online; Teachers can use/adopt as part of their teaching material. This course is offered at Jaypee University of Engineering & Technology (JUET). URL : http://www.myreaders.info/html/soft_computing.html ; 3 . Course objectives : Conditions of use : Creative Commons Attribution-Noncommercial-No Derivative Works 2.5. [Ref. http://www.oercommons.org/courses/soft-computing ] (i) The material offers online learning resources for students. (ii) A teacher can use/adopt as part of their teaching material. (iii) The lecture slides, notes includes traditional explanatory text, tables, diagrams, examples, algorithms, pseudo codes and book references. (iv) The Learning objectives are (a) Learn the general concepts and techniques in soft computing; how to apply some of the techniques to practical problems; Learn intelligent exploitation of random search used to solve optimization problems. The focus is on theory and application of neural network, fuzzy logic and genetic algorithms in handling problems which are not modeled or too difficult to model mathematically or define algorithmically (b) The course intends to teach - Introduction to Soft Computing; Fundamentals of neural network; Back propagation network; Associative memory; Adaptive resonance theory; Fuzzy set theory; Fuzzy systems; Fundamentals of genetic algorithms; and Hybrid systems. (c) At the end of this course, the student will be have fairly good understanding of fusion of methodologies designed to model and enable solutions to real world problems; exploit the tolerance for imprecision, uncertainty, approximate reasoning, and partial truth in close resemblance with human like decision making. (v) Skills desired - familiar with earlier course on Artificial Intelligence; problem solving, search and control strategies; knowledge representation issues - predicate logic, rules; reasoning system - symbolic, statistical; learning systems; and expert systems. Conditions of Use : Creative Commons Attribution-Noncommercial-No Derivative Works 2.5 [Ref. http://www.oercommons.org/courses/soft-computing ]