Neural Networks and Fuzzy Logic detailed syllabus scheme for Electronics & Telecommunication Engineering (EC), 2019 regulation has been taken from the MU official website and presented for the Bachelor of Engineering students. For Course Code, Course Title, Test 1, Test 2, Avg, End Sem Exam, Team Work, Practical, Oral, Total, and other information, do visit full semester subjects post given below.
For 7th Sem Scheme of Electronics & Telecommunication Engineering (EC), 2019 Pattern, do visit EC 7th Sem Scheme, 2019 Pattern. For the Department Level Optional Course-3 scheme of 7th Sem 2019 regulation, refer to EC 7th Sem Department Level Optional Course-3 Scheme 2019 Pattern. The detail syllabus for neural networks and fuzzy logic is as follows.
Neural Networks and Fuzzy Logic Syllabus for Electronics & Telecommunication Engineering BE 7th Sem 2019 Pattern Mumbai University
Prerequisites:
For the complete Syllabus, results, class timetable, and many other features kindly download the iStudy App
It is a lightweight, easy to use, no images, and no pdfs platform to make students’s lives easier.
.
Course Objectives:
- To introduce the concepts and understanding of artificial neural networks
- To provide adequate knowledge about supervised and unsupervised neural networks
- To introduce neural network design concepts
- To expose neural networks based methods to solve real world complex problems
- To teach about the concept of fuzziness involved in various systems and provide adequate knowledge about fuzzy set theory, and fuzzy logic
- To provide knowledge of fuzzy logic to design the real world fuzzy systems
Course Outcomes:
After successful completion of the course student will be able to
- Comprehend the concepts of biological neurons and artificial neurons
- Analyze the feed-forward and feedback neural networks and their learning algorithms.
- Calculate Comprehend the neural network training and design concepts
- Analyze the application of neural networks to non linear real world problem
- Comprehend the concept of fuzziness involved in various systems, fuzzy set theory and fuzzy logic
- Apply fuzzy logic to real world problems.
Module 1
For the complete Syllabus, results, class timetable, and many other features kindly download the iStudy App
It is a lightweight, easy to use, no images, and no pdfs platform to make students’s lives easier..
Module 2
Supervised Learning Neural Networks: 08
- Perceptron – Single Layer, Multilayer and their architecture, Error back propagation algorithm, Generalized delta rule, Concept of Training, Testing and Cross-validation data sets for design and validation of networks. Over-fitting. Stopping criterion for training.
Module 3
Unsupervised Learning Neural Networks: 09
- Competitive Learning Networks – Maxnet, Mexican Hat Net, Kohonen Self-Organizing Networks – architecture, training algorithm, K-means and LMS algorithms, Radial Basis Function (RBF) neural network -architecture and algorithm, and Discrete Hopfield networks. Introduction to the concept of Support Vector Machine based classifier.
Module 4
For the complete Syllabus, results, class timetable, and many other features kindly download the iStudy App
It is a lightweight, easy to use, no images, and no pdfs platform to make students’s lives easier..
Module 5
Fuzzy logic: 12
- Introduction to fuzzy logic, Basic Fuzzy logic theory, Fuzzy sets -properties & operations, Fuzzy relation – Operations on fuzzy relations, Fuzzy Membership functions, Fuzzy Rules and Fuzzy Reasoning, Fuzzification and Defuzzification methods, Fuzzy Inference Systems, Mamdani Fuzzy Models, Fuzzy knowledge based controllers.
Module 6
Applications of Fuzzy Logic and Fuzzy Systems: 06
- Fuzzy pattern recognition, fuzzy image processing, Simple applications of Fuzzy knowledge based controllers like washing machines, home heating system, and train break control.
Text Books:
For the complete Syllabus, results, class timetable, and many other features kindly download the iStudy App
It is a lightweight, easy to use, no images, and no pdfs platform to make students’s lives easier..
Reference Books:
- Hagan, Demuth, and Beale, Neural Network Design, Thomson Learning
- Simon Haykin, Neural Network- A Comprehensive Foundation, Pearson Education
- Christopher M Bishop, Neural Networks For Pattern Recognition, Oxford University Press
- William W Hsieh, Machine Learning Methods in the Environmental Sciences Neural Network and Kernels, Cambridge Publications
- S. N. Sivanandam, S. Sumathi, and S. N. Deepa, Introduction to Neural Network Using Matlab Tata McGraw-Hill Publications
- Bart Kosko, Neural networks and Fuzzy Systems, Pearson Education
- J. S. R. Jang, C.T. Sun, and E. Mizutani, Neuro-Fuzzy and Soft Computing, PHI
- J. M. Zurada, Introduction to Artificial Neural Systems, Jaico publishers
Internal Assessment:
Assessment consists of two class tests of 20 marks each. The first class test is to be conducted when approximately 40% syllabus is completed and second class test when additional 40% syllabus is completed. The average marks of both the test will be considered for final Internal Assessment. Duration of each test shall be of one hour.
End Semester Examination:
- Question paper will comprise of 6 questions, each carrying 20 marks.
- The students need to solve total 4 questions.
- Question No.1 will be compulsory and based on entire syllabus.
- Remaining question (Q.2 to Q.6) will be selected from all the modules.
For detail Syllabus of all subjects of Electronics & Telecommunication Engineering (EC) 7th Sem 2019 regulation, visit EC 7th Sem Subjects of 2019 Pattern.