MTech Neural Network And Fuzzy Logic In Medicine syllabus for 2 Sem 2020 scheme 20LBI23

Module-1 Learning and Soft Computing 0 hours

Learning and Soft Computing:

Examples, basic tools of soft computing, basic mathematics of soft computing, Differences between neural network and Biological neural network, Network Architecture, Artificial Intelligent Learning process :Error correction Algorithm, Memory based Learning, Hebian Learning, Learning with Teacher, Learning without Teacher

Module-2 Single Layer Networks 0 hours

Single Layer Networks:

Perception, Perceptron Convergence theorem, Realization of Basic logic gates using single layer Perceptron, Adaptive linear neuron (Adaline) and the LMS algorithm.

A d v e r t i s e m e n t
Module-3 Multilayer Perception 0 hours

Multilayer Perception:

Error back propagation algorithm, generalized delta rule, XOR Problem, Practical Aspects of Error Back Propagation Algorithm. Problems

 

Radial Basis Function Networks:

Ill Posed Problems and Regularization Technique, Stabilizers and Basis Functions, Generalized Radial Basis Function Networks.

Module-4 Support Vector Machines 0 hours

Support Vector Machines :

Risk minimization principles and the Concept of Uniform Convergence, VC dimension, Structural Risk Minimization, support vector machine algorithms

Fuzzy Logic:

Introduction to Fuzzy Logic, Classical and Fuzzy Sets: Overview of Classical Sets, Membership Function, Operations on Fuzzy Sets, Fuzzy Arithmetic, Compliment, Intersections, Unions, Fuzzy Relation.

Module-5 Fuzzy Rule based system 0 hours

Fuzzy Rule based system

Linguistic Hedges. Rule based system, Graphical techniques for Inference, Fuzzification and Defuzzification, fuzzy additive models Applications.

 

Case studies:

Fuzzy logic control of Blood pressure during Anaesthesia, Fuzzy logic application to Image processing equipment, Adaptive fuzzy system. Introduction to Neuro-fuzzy logic tool using LabView

 

Course Outcomes:

After completion of this course the student will be able to:

1. Compare the difference between biological and artificial neural network.

2. Describe regression and classification method

3. Describe Single layer initialize theorem

4. Analyze the generalized radial basis function networks.

 

Question Paper Pattern:

  • The SEE question paper will be set for 100 marks and the marks scored will be proportionately reduced to 60.
  • The question paper will have ten full questions carrying equal marks.
  • Each full question is for 20 marks.
  • There will be two full questions (with a maximum of four sub questions) from each module.
  • Each full question will have sub question covering all the topics under a module.
  • The students will have to answer five full questions, selecting one full question from each module.

 

Textbooks:

1. S. Haykin, “Neural networks: A Comprehensive Foundation”’ Pearson Education (Asia) Pvt. Ltd/Prentice Hall of India, 2003.

2. Timothy J Ross, “Fuzzy logic with Engineering Applications”, McGraw Hill Publication, 2000.

3. Bart Kosko, “Neural Networks and Fuzzy Systems”, Prentice Hall of India, 2005

 

Reference Books:

1. Vojislav Kecman, “Learning and soft computing”, Pearson Education (Asia) Pvt. Ltd.2004.

2. M.T.Hagan, H.B.Demuth and M. Beale, “Neural Network Design”, Thomson Learning, 2002.

3. George J. Klir and Bo Yaun, “Fuzzy sets and Fuzzy Logic: Theory and Application”, Prentice Hall of India, 2001.

Categories

VTU Updates