Artificial Neural Networks and Fuzzy Logic Syllabus for VTU BE 2017 Scheme (Open Elective-2)

Artificial Neural Networks and Fuzzy Logic detail syllabus for various departments, 2017 scheme is taken from VTU official website and presented for VTU students. The course code (17EE661), and for exam duration, Teaching Hr/week, Practical Hr/week, Total Marks, internal marks, theory marks, duration and credits do visit complete sem subjects post given below.

For all other open elective-2 syllabus for vtu be 2017 scheme you can visit Open Elective-2 syllabus for VTU BE 2017 Scheme Subjects. The detail syllabus for artificial neural networks and fuzzy logic is as follows.

Course Objectives:

• To expose the students to the concepts of feed forward neural networks.
• To provide adequate knowledge about feedback networks.
• To teach about the concept of fuzziness involved in various systems.
• To provide adequate knowledge about fuzzy set theory

Module 1

For complete syllabus and results, class timetable and more pls download iStudy. Its a light weight, easy to use, no images, no pdfs platform to make students life easier.

Module 2

Back propagation Networks (continued): Effect of Tuning Parameters of the Back propagation Neural Network, Selection of Various Parameters in BPN, Variations of Standard Back propagation Algorithm. Associative Memory: Auto correlators, Hetero correlators: Kosko’s Discrete BAM, Wang et al.’s Multiple Training Encoding Strategy, Exponential BAM, Associative Memory for Real-coded Pattern Pairs, Applications, Recent Trends.

Module 3

Adaptive Resonance Theory: Introduction, ART l, ART 2, Applications, Sensitivities of Ordering of Data,

Module 4
For complete syllabus and results, class timetable and more pls download iStudy. Its a light weight, easy to use, no images, no pdfs platform to make students life easier.

Module 5

Fuzzy Logic And Inference: Crisp Logic, Predicate Logic, Fuzzy Logic, Fuzzy Rule based System, Defuzzification Methods, Applications. Type – 2 Fuzzy Sets: Representation of Type – 2 Fuzzy Sets, Operations on Type – 2 Fuzzy Sets, Interval Type – 2 Fuzzy Sets.

Course Outcomes:

At the end of the course the student will be able to:

• Show an understanding of Organization of the Brain, Biological and Artificial Neuron Models
• Show an understanding of Back propagation network architecture, Perceptron Model, Single layer Artificial Neural Network, Model for Multilayer Perceptron, Back propagation Learning,
• Show an understanding of Back propagation training and summary of Back propagation Algorithm
• Show an understanding Bidirectional Associative Memory (BAM) Architecture
• Show an understanding adaptive resonance theory architecture and its applications
• Differentiate between crisp logic, predicate logic and fuzzy logic.
• Explain fuzzy rule based system
• Show an understanding of Defuzzification methods

Graduate Attributes (as per NBA):

• Engineering Knowledge,
• Problem Analysis,

Question paper pattern:

• The question paper will have ten questions.
• Each full question is for 16 marks.
• There will be 2full questions (with a maximum of four sub questions in one full question) from each module.
• Each full question with sub questions will cover the contents under a module.
• Students will have to answer 5 full questions, selecting one full question from each module

Text Books:

1. Neural Networks, Fuzzy Systems and Evolutionary Algorithms: Synthesis and ApplicationsS. Rajasekaran, G.A. VijayalakshmiPai PHI Learning 2nd Edition, 2017

Reference Books:

1. Neural Networks – A comprehensive foundation Simon Haykin Prentice Hall 3rd Edition, 2004.
2. Fuzzy Logic With Engineering Applications Timothy J Ross Wiley 3rd Edition, 2014
3. Fuzzy sets and Fuzzy Logic: Theory and Applications Klir, G.J. Yuan Bo Prentice Hall 2005.

For detail syllabus of all other subjects of BE do syllabus for different schemes from menu given on top.

Dont forget to download iStudy for latest syllabus and results, class timetable and more.