University of Mumbai Syllabus For Semester 7 (BE Fourth Year) Soft Computing: Knowing the Syllabus is very important for the students of Semester 7 (BE Fourth Year). Shaalaa has also provided a list of topics that every student needs to understand.

The University of Mumbai Semester 7 (BE Fourth Year) Soft Computing syllabus for the academic year 2021-2022 is based on the Board's guidelines. Students should read the Semester 7 (BE Fourth Year) Soft Computing Syllabus to learn about the subject's subjects and subtopics.

Students will discover the unit names, chapters under each unit, and subtopics under each chapter in the University of Mumbai Semester 7 (BE Fourth Year) Soft Computing Syllabus pdf 2021-2022. They will also receive a complete practical syllabus for Semester 7 (BE Fourth Year) Soft Computing in addition to this.

## University of Mumbai Semester 7 (BE Fourth Year) Soft Computing Revised Syllabus

University of Mumbai Semester 7 (BE Fourth Year) Soft Computing and their Unit wise marks distribution

### University of Mumbai Semester 7 (BE Fourth Year) Soft Computing Course Structure 2021-2022 With Marking Scheme

# | Unit/Topic | Marks |
---|---|---|

C | Introduction to Soft Computing | |

CC | Neural Networks | |

201 | Basics of Neural Networks | |

202 | Supervised Learning Algorithms | |

203 | Un-supervised Learning Algorithms | |

CCC | Fuzzy Set Theory | |

CD | Hybrid System | |

D | Introduction to Optimization Techniques | |

DC | Genetic Algorithms and Its Applications | |

Total | - |

## Syllabus

- Soft computing Constituents, Characteristics of Neuro Computing and Soft Computing, Difference between Hard Computing and Soft Computing, Concepts of Learning and Adaptation.

- Introduction to Neural Networks, Biological Neural Networks, McCulloch Pitt model.

- Perceptron (Single Layer, Multi layer), Linear separability, Delta learning rule, Back Propagation algorithm.

- Hebbian Learning, Winner take all, Self Organizing Maps, Learning Vector Quantization.

- Classical Sets and Fuzzy Sets, Classical Relations and Fuzzy Relations, Properties of membership function, Fuzzy extension principle, Fuzzy Systems- fuzzification, defuzzification and fuzzy controllers.

- Introduction to Hybrid Systems, Adaptive Neuro Fuzzy Inference System (ANFIS).

- Derivative based optimization- Steepest Descent, Newton method.
- Derivative free optimization- Introduction to Evolutionary Concepts.

- Inheritance Operators, Cross over types, inversion and Deletion, Mutation Operator, Bit-wise Operators, Convergence of GA, Applications of GA.