Course Information:
Course Title: Neural Networks and Fuzzy Systems
Course Code: CSE 4203
Credit: 3.00 (Three Hours per Week)
Year and Semester: 4th Year Even Semester
Course Rationale:
This course aims at introducing the fundamental theory and concepts of computational intelligence methods, in particular neural networks, fuzzy systems, genetic algorithms and their applications in the area of machine intelligence. This will help students to get sufficient knowledge to analyze and design the various intelligent control systems in real world scenarios.
Course Content / Course Description:
Introductory Concept: Introduction Human Brain Mechanism, Neural Machine Intelligence.
Fundamental Concept of Neural Network: Basic Models of Artificial Neuron, Activation Function, Network Architecture, Neural Network Viewed as Directed Graph, Basic Learning Rules, Overview of Perceptrons, Single Layer of Perceptrons, Mathematical Model of Single Layer Perceptrons, Perceptrons Learning Algorithm, Delta Learning Rule, Multi-Layer Perceptrons, Back Propagation Learning Algorithm, Mathematical Model of MLP Network.
Function Approximation: Basis Function Network, Radial Basis Function Networks (RBF), MLP vs. RBF Networks, Support Vector Machine (SVM).
Competitive Network and Associative Memory Network: Adaptive Resonance Theory (ART), ART-1 Architecture and Algorithm, Kohonen Self-Organizing Maps (SOMs), Linear Feed-Forward Associative Memory Network, Recurrent Associative Memory Network, Bidirectional Associative Memory Network (BAM), Hopfield Networks.
Fuzzy System: Introduction to Fuzzy System, Fuzzy Relations, Fuzzy Numbers, Linguistic Description and their Analytical Form, Fuzzy Control.
Defuzzification: Defuzzification Methods, Centroid Method, Center of Sum Method, Mean of Maxima Defuzzification, Applications, Equilibrium of Learning System, Concept of Neuro-Fuzzy and Neuro-GA Network.
Genetic Algorithm: Basic Concepts, Offspring, Encoding, Reproduction, Crossover, Mutation Operator, Application of GA
References:
SL No. : 1
Text Book Name: Neural Computing - An Introduction
Writer Name: R Beale and T Jackson
Publisher: Adam Hilger, 1990 IOP Publishing Ltd.
SL No. : 2
Text Book Name: C++ in Neural Networks and Fuzzy Logic
Writer Name: Valluru B. Rao
Publisher: M&T Books, IDG Books Worldwide, Inc.
SL No. : 3
Text Book Name: Genetic Algorithms in Search, Optimization and Machine Learning
Writer Name: David E. Goldberg
Publisher: Addison-Wesley Publishing Company, INC.
Lecture Plan:
Week no. : 1
Contact Hours : 3 Hours Per Week
Topics: Introductory Concept: Introduction Human Brain Mechanism, Neural Machine Intelligence.
Week no. : 2
Contact Hours : 3 Hours Per Week
Topics: Fundamental Concept of Neural Network: Basic Models of Artificial Neuron, Activation Function, Network Architecture, Neural Network Viewed as Directed Graph.
Week no. : 3
Contact Hours : 3 Hours Per Week
Topics: Fundamental Concept of Neural Network: Basic Learning Rules, Overview of Perceptrons, Single Layer of Perceptrons, Mathematical Model of Single Layer Perceptrons.
Week no. : 4
Contact Hours : 3 Hours Per Week
Topics: Class Test – 1 (Time: As per Department routine)
Fundamental Concept of Neural Network: Perceptrons Learning Algorithm, Delta Learning Rule, Multi-Layer Perceptrons, Back Propagation Learning Algorithm, Mathematical Model of MLP Network.
Week no. : 5
Contact Hours : 3 Hours Per Week
Topics: Function Approximation: Basis Function Network, Radial Basis Function Networks (RBF), MLP vs. RBF Networks, Support Vector Machine (SVM).
Week no. : 6
Contact Hours : 3 Hours Per Week
Topics: Competitive Network and Associative Memory Network: Adaptive Resonance Theory (ART), ART-1 Architecture and Algorithm, Kohonen Self-Organizing Maps (SOMs).
Week no. : 7
Contact Hours : 3 Hours Per Week
Topics: Class Test – 2 (Time: As per Department routine)
Competitive Network and Associative Memory Network: Linear Feed-Forward Associative Memory Network, Recurrent Associative Memory Network, Bidirectional Associative Memory Network (BAM), Hopfield Networks
Week no. : 8
Contact Hours : 3 Hours Per Week
Topics: Fuzzy System: Introduction to Fuzzy System, Fuzzy Relations, Fuzzy Numbers, Linguistic Description and their Analytical Form, Fuzzy Control.
Week no. : 9
Contact Hours : 3 Hours Per Week
Topics: Defuzzification: efuzzification Methods, Centroid Method, Center of Sum Method, Mean of Maxima Defuzzification, Applications.
Week no. : 10
Contact Hours : 3 Hours Per Week
Topics: Defuzzification: Equilibrium of Learning System, Concept of Neuro-Fuzzy and Neuro-GA Network.
Week no. : 11
Contact Hours : 3 Hours Per Week
Topics: Class Test – 3 (Time: As per Department routine)
Genetic Algorithm: Basic Concepts, Offspring, Encoding, Reproduction, Crossover, Mutation Operator. Application of GA.
Week no. : 12
Contact Hours : 3 Hours Per Week
Topics: Genetic Algorithm: Application of GA.
Week no. : 13
Contact Hours : 3 Hours Per Week
Topics: Class Test – 4 (Time: As per Department routine)
Revision: All topics that’s are conducted in this course.
Assessment & Marks Distribution:
Attendance: 8
Class Test: 20 (average on the Best of Three among 4 class test)
Semester Final: 72
Total Marks: 100
Grading Policy:
% of Marks Letter Grade Point
80 – 100 A+ 4.00
75 – 79 A 3.75
70 – 74 A- 3.50
65 – 69 B+ 3.25
60 – 64 B 3.00
55 – 59 B- 2.75
50 – 54 C+ 2.50
45 – 49 C 2.25
40 – 44 D 2.00
0 – 39 F 0.00
Additional Course Policy:
Class test: For this course, four class tests will be held and each class test marks are 20. Best three class tests average mark is counted as the score of class test. Books, class notes are not allowed at the time of exam. Mobile phone is strictly prohibited in the exam hall.
Semester Final: For this course, semester final exam will be held according to exam routine at end of this course. Semester final exam contains 72 marks and books, class notes are not allowed at the time of exam. Mobile phone is strictly prohibited in the exam hall.
Students Policy with Physically Handicapped:
Students with disabilities are required to inform the Department of Computer Science & Engineering of any specific requirement for classes or examination as soon as possible
Resources:
Notice:
Course Title: Sessional Based on CSE CSE 4203
Course Code: CSE 4204
Credit: 0.75 (2.5 hours per alternative week)
Year and Semester: 4th Year Even Semester
Course Rationale:
The aim of this course is to analyze the characteristics of neural networks, fuzzy logic and genetic algorithms to provide intelligence into the machine. The students will learn to analyze, design and develop Artificial Intelligence (AI) related solutions according to real world problems. AI related different machine learning tools, techniques and libraries will be introduced in this course.
Course Content / Course Description:
In this course, theoretical knowledge is implemented in the laboratory based on the course CSE – 4203 (Neural Networks and Fuzzy Systems). Lab experiments are designed according to the theory course. At the end of this course, students are able to design various neural networks algorithms, Fuzzy logic controllers and genetic algorithms for different real world problem solutions.
References:
SL No. : 1
Text Book Name: Neural Computing - An Introduction
Writer Name: R Beale and T Jackson
Publisher: Adam Hilger, 1990 IOP Publishing Ltd.
SL No. : 2
Text Book Name: C++ in Neural Networks and Fuzzy Logic
Writer Name: Valluru B. Rao
Publisher: M&T Books, IDG Books Worldwide, Inc.
SL No. : 3
Text Book Name: Genetic Algorithms in Search, Optimization and Machine Learning
Writer Name: David E. Goldberg
Publisher: Addison-Wesley Publishing Company, INC.
Lecture Plan:
Week no. Contact Hours Name of the Experiments:
1 2.5 Hours Implementation of Nearest Neighbor classification algorithms with and without distorted pattern.
2 2.5 Hours Design and implementation of single layer perceptron learning algorithm.
3. 2.5 Hours Design and implementation of Multi-layer Neural Networks algorithm (i.e., Back-propagation learning neural networks algorithm).
4. 2.5 Hours (1) Design and implementation of Kohonen Self-organizing Neural Networks algorithm.
(2) Design and implementation of Hopfield Neural Networks algorithm.
5. 2.5 Hours Designing a Fuzzy Logic Controller (FLC) for controlling the environmental inputs to solve the real world problem.
6. 2.5 Hours Design and development of a Genetic Algorithm (GA) to search and optimize a specific problem.
7. 2.5 Hours Quiz/ Viva voce will be held during the Lab time.
Assessment & Marks Distribution:
Attendance: 8
Quiz : 20
Lab Performance / Report: 47
Board Viva (Compulsory): 25
Total Marks: 100
Grading Policy:
% of Marks Letter Grade Point
80 – 100 A+ 4.00
75 – 79 A 3.75
70 – 74 A- 3.50
65 – 69 B+ 3.25
60 – 64 B 3.00
55 – 59 B- 2.75
50 – 54 C+ 2.50
45 – 49 C 2.25
40 – 44 D 2.00
0 – 39 F 0.00
Additional Course Policy:
Quiz : For this course, a quiz will be held at the end of this coursethat will contain 20 marks. By the quiz test, your basic knowledge and performance test of the lab will be evaluated. True/False question, fill in the blacks, MCQ and CBQ may be included in the quiz question.
Assessment: In every lab, we assess you based on your lab working performance along with the lab report and at the end of the labs all marks of the performance is summed up and scaled to 47. This segment contains a total 47 marks.
Board Viva: For this course, a board viva along with other sessional courses in this semester will be held according to the routine at the end of this course. Board viva is compulsory and it contains 25 marks.
Students Policy with Physically Handicapped:
Students with disabilities are required to inform the Department of Computer Science & Engineering of any specific requirement for classes or examination as soon as possible
Notice: