Scribd
Upload
252 views4 pages

ECE661 Artificial Intelligence and Fuzzy Systems Syllabus

This course provides an introduction to artificial intelligence techniques including artificial neural networks, fuzzy systems, neuro-fuzzy modeling, and genetic algorithms. The course aims to teach the principles and applications of these techniques. It is composed of 5 modules that cover topics such as neural network architectures, backpropagation networks, fuzzy logic concepts, fuzzy membership functions, and genetic algorithms. Students will complete programming assignments and experiments in MATLAB to design and analyze neural networks, fuzzy systems, and genetic algorithms. Assessment includes a midterm exam, assignments, labs, and a final exam.

Uploaded by

paku dey
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
252 views4 pages

ECE661 Artificial Intelligence and Fuzzy Systems Syllabus

This course provides an introduction to artificial intelligence techniques including artificial neural networks, fuzzy systems, neuro-fuzzy modeling, and genetic algorithms. The course aims to teach the principles and applications of these techniques. It is composed of 5 modules that cover topics such as neural network architectures, backpropagation networks, fuzzy logic concepts, fuzzy membership functions, and genetic algorithms. Students will complete programming assignments and experiments in MATLAB to design and analyze neural networks, fuzzy systems, and genetic algorithms. Assessment includes a midterm exam, assignments, labs, and a final exam.

Uploaded by

paku dey
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

L T P/ SW/FW TOTAL

Course Title: Artificial Intelligence & Fuzzy Systems S CREDIT UNITS


Course Code: ECE661
Credit Units: 4 3 0 2 0 4
Level: PG

Course Objective:
The course aims to provide knowledge of artificial neural networks, Fuzzy systems,Neuro-fuzzy modeling and Genetic algorithms.
The problems and techniques of A.I. along with the applications of A.I are discussed. The students will learn the principles of neural
networks, fuzzy systems& GAs; neural dynamics; activations and signals; activation models; unsupervised and supervised learning
rules and their domain of applications; architectures of neural systems.
Prerequisites:
Basics of calculus and classical set theory

Weightage (%)
Module I Neural Networks-1(Introduction & Architecture) 20%
Neuron, Nerve structure and synapse, Artificial Neuron and its model, activation functions.
Neural network architecture: single layer and multilayer feed forward networks, recurrent networks. Various
learning techniques; perception and convergence rule.
Module II Neural Networks-II (Back propagation networks 20%
Architecture: perceptron model, solution, single layer artificial neural network, multilayer perception model;
back propagation learning methods, effect of learning rule co-efficient ;back propagation algorithm, factors
affecting back propagation training, applications.
Module III Fuzzy Logic-I (Introduction) 20%
Basic concepts of fuzzy logic, Fuzzy sets and Crisp sets, Fuzzy set theory and operations, Properties of fuzzy
sets, Fuzzy and Crisp relations, Fuzzy to Crisp conversion.

Module IV Fuzzy Logic –II (Fuzzy Membership, Rules) 20%


Membership functions, interference in fuzzy logic, fuzzy if-then rules, Fuzzy implications and Fuzzy
algorithms, Fuzzification&Defuzzification, Fuzzy Controller, Industrial applications.
Module V Genetic Algorithms (GA) 20%
Basic concepts, working principle, procedures of GA, flow chart of GA, Genetic representations, (encoding)
Initialization and selection, Genetic operators, Mutation, Generational Cycle, applications.

Student Learning Outcomes:


 Design ANN architectures for scientific and industrial applications.
 Analyze practical situations involving ambiguity and implement fuzzy solutions, subject to standard/specified criteria.
 Develop methods based on the use of GAs to solve optimization problems.

Pedagogy for Course Delivery:


The class will be taught using theory and case-based method. In addition to assigning students individual library-research projects, the
course instructor will spend considerable time in grounding them, being first-time-learners, in the concepts of soft computing.

List of Experiments (using MATLAB)

1. Write a Program to generate a few activation functions used in NNs.


2. Generate XOR function using McCulloch-Pitts model.
3. Write a Program for a Perceptron net using bipolar inputs and targets for AND function.
4. Write a program to store the vector (-1111). Find the weight matrix, with no self-connection. Use a discrete Hopfield net to
test this, with mistakes in the second and third component, i.e. (0001).
5. Using the Back-propagation algorithm, write an M-file, for XOR function, using momentum sector.
6. Develop OR function, using Hebb net, with binary inputs and bipolar targets.
Open-ended experiments :
7. Approximate a two-D function, in batch mode, using BP learning. (Before starting, show the function chosen, to the
instructor).
8. Using the Kohonen algorithm, develop a program, to form feature maps.
9. Draw a self-organizing feature map, in two-D, with the help of the program in Expt. No. 8. ( Modify it where required).
10. Write a program, for a Hebbnet, to classify two-D input patterns. Test for a known problem with bipolar inputs and suitable
targets. Use ‘*’ for +1 and ‘.’ for -1.

Assessment/ Examination Scheme:


Theory L/T (%) Lab/Practical/Studio (%) Total

75% 25% 100%

Theory Assessment (L&T):


Continuous Assessment/Internal Assessment

Components End Term Examination


(Drop down)
Mid-Term Exam Assignment Viva Attendance

Weightage (%)
70%
10% 7% 8% 5%

Lab Assessment (P):


Continuous Assessment/Internal Assessment

Components External Assessment

(Drop down) Attendance PR LR Viva

Weightage (%)
5% 10% 10% 5% 70%

A: Attendance, PR- Performance, LR – Lab Record, V – Viva. EE- External Exam,


Text & References:
 Simon Nuykin, Neural Netwoks – a Comprehensive Foundation, IInd Editor, PHI 2008 (Rs. 375)
 S.Rajasetaran, G.A. VijaylakshmiRai, Neural Networks, Fuzzy Logic and Genetic Algorithms- Synthesis and Application,
PHJ, 2008 Reference (Rs. 325)
 Martin T. Hagan, Howard B. Demuth and Mark Beale, “Neural Network Design,” (Engage Learning 2008)
 Laurence Fausff, “Fundamentals of Neural Networks – architecture algorithms and Application. Pearson Education, 1994.
 James A. Frceman& David M. Skapura, “Neural networks- algorithms, application and programming techniques, 1991”.
 Mohamad H. Hassouh, “ Fundamentals of Artificial Neural network, PHI 2003 (Rs. 295 Indian Rupees)
 S.N.Sivanandam, S. Sumathi and S.N. Deepa, “Neural Networks using Matlab B 60, Talamegian H.11 2006.

You might also like