|13040708||Neural Networks and Fuzzy||L||T||P||C|
|Version1.1||Date of Approval: Jun 06, 2013||3||1||0||3|
After the completion of course the students will
- Get the exposure to Artificial Neural Networks & Fuzzy Logic.
- Understand the importance of tolerance of imprecision and uncertainty for design of robust & low cost intelligent machines.
On completion of this course, the students will be able to
- Identify and describe Fuzzy Logic and Artificial Neural Network techniques in building intelligent machines
- Apply Artificial Neural Network & Fuzzy Logic models to handle uncertainty and solve engineering problems.
- Recognize the feasibility of applying a Neuro-Fuzzy model for a particular problem
The objective of this course is to present sufficient background in both fuzzy and neural network so that students in future can pursue advanced soft computing methodologies. This course combines knowledge, techniques, and methodologies from various sources, using techniques from neural networks and fuzzy set theory, As an extension, the course uses the Neuro Fuzzy models for the complex engineering problems.
- Ross, Timothy J. Fuzzy logic with engineering applications. John Wiley & Sons, 2009.
- Yegnanarayana, B. Artificial neural networks. PHI Learning Pvt. Ltd., 2004.
- Zurada, Jacek M. Introduction to artificial neural systems, West St. Paul, 1992.
- Hagan, Martin T., Howard B. Demuth, and Mark H. Beale. Neural network design. Boston: Pws Pub., 1996.
- Haykin, Simon. Neural networks: a comprehensive foundation. Prentice Hall PTR, 1994.
- Passino, Kevin M., and Stephen Yurkovich. Fuzzy control. Vol. 42. Menlo Park, CA: Addison-Wesley, 1998.
Unit I: Introduction to Artificial Neural Network
9 lecture hours
Artificial neural networks and their biological motivation: Terminology, Models of neuron, Topology, characteristics of artificial neural networks, types of activation functions; learning methods: error correction learning, Hebbian learning, Perceptron: XOR Problem, Perception learning rule convergence theorem; Adaline.
Unit II: Feedforward and Recurrent Neural Networks
9 lecture hours
Architecture: perceptron model, solution, single layer artificial neural network, multilayer
perceptron model; back propogation learning methods, effect of learning rule co-efficient ;back propagation algorithm, factors affecting backpropagation training, applications; Recurrent neural networks: Linear auto associator – Bi-directional associative memory – Hopfield neural network.
Unit III: Fuzzy Logic & Fuzzy Sets
8 lecture hours
Introduction to Fuzzy Logic, Classical and Fuzzy Sets, Membership Function ,Membership Grade, Universe of Discourse, Linguistic Variables, Operations on Fuzzy Sets: Intersections, Unions, Negation, Product, Difference, Properties of Classical set and Fuzzy sets, Fuzzy vs Probability, Fuzzy Arithmetic, Fuzzy Numbers.
Unit IV: Fuzzy Relations & Aggregations
8 lecture hours
Essential Elements of Fuzzy Systems, Classical Inference Rule, Classical Implications and Fuzzy Implications, Crisp Relation and Fuzzy Relations, Composition of fuzzy relations, Cylindrical Extension and Projection. Fuzzy IF-THEN rules, Inference: Scaling and Clipping Method, Aggregation, Fuzzy rule based Model: Mamdani Model, TSK model, Fuzzy Propositions, Defuzzification: MOM, COA
Unit V: Fuzzy Optimization and Neuro Fuzzy Systems
6 lecture hours
Fuzzy optimization –one-dimensional optimization. Introduction of Neuro-Fuzzy Systems, Architecture of Neuro Fuzzy Networks.
Mode of Evaluation: The theory performance of students are evaluated .
|Theory||Theory and laboratory|
Relationship between the Course Outcomes (COs) and Program Outcomes (POs)
|Mapping between COs and POs|
|Sl. No.||Course Outcomes (COs)||Mapped Programme Outcomes|
|1||Identify and describe Fuzzy Logic and Artificial Neural Network techniques in building intelligent machines
|2||Apply Artificial Neural Network & Fuzzy Logic models to handle uncertainty and solve engineering problems.
|3||Recognize the feasibility of applying a Neuro-Fuzzy model for a particular problem
|Engineering Knowledge||Problem analysis||Design/development of solutions||Conduct investigations of complex problems||Modern tool usage||The engineer and society||Environment and sustainability||Ethics||Individual or team work||Communication||Project management and finance||Life-long Learning|
|TEC461||Neural Networks and Fuzzy Control||2||3||2|
1=addressed to small extent
2= addressed significantly
3=major part of course
|Theory||The theory of this course is used to evaluate the program outcome PO(2)|