INSTRUCTION DIVISION
FIRST/ SECOND SEMESTER 2019-20
Course Handout
Date: 13-07-2019
Course No. : BITS F312
Course Title : Neural Network and Fuzzy Logic
Instructor-in-Charge : Dr. Rajesh Kumar Tripathy
1. Scope and Objective of the Course:
This course introduces several fundamental concepts of artificial neural network and fuzzy logic. The objective
is to familiarize the students with some basic learning algorithms and techniques and their applications, as well
as general questions related to analyzing and handling large data sets. Several software libraries and datasets
publicly available will be used to illustrate the application of these algorithms. In this course, the various
supervised learning algorithms such as logistic regression, multiclass logistic regression, multilayer perceptron,
radial basis function neural network, extreme learning machine and the deep neural network will be discussed.
By the end of this course, students will have a strong understanding of artificial neural network based techniques
for various real-time applications.
2. Textbooks:
T1. Simon Haykin, “Neural Networks – A comprehensive Foundation”, Pearson Education, 1999.
T2. H. J. Zimmermann, “Fuzzy Set Theory and its Applications”,3rd Edition, Kluwer Academic, 1996.
3. Reference books/Materials
R1: CS229 Lecture notes: Stanford University
R2: CS231 Convolutional neural networks for visual recognition: Stanford University
R3: http://gyan.iitg.ernet.in/handle/123456789/833
R4: https://www.sciencedirect.com/science/article/pii/S0925231206000385
R5: https://www.springer.com/cda/content/document/cda_downloaddocument/9783319284354-
c2.pdf?SGWID=0-0-45-1545215-p177863021
4. Course Plan:
Chapter in the
Lecture No. Topics to be covered
Text Book
Introduction to machine learning, Supervised, unsupervised and
1 T1 (ch 2)
semi-supervised learning,
Classification and regression problems, Linear regression,
2-4 gradient descent (Batch gradient descent and stochastic gradient R1
descent)
Logistic regression, multiclass extension of logistic regression
5-8 R1
(One Vs One and One Vs All Multiclass coding schemes)
Performance Measures for Classifiers (binary class and
9 R3 (2.9.5)
multiclass), Probabilistic classifiers
What is Neural Network?, Human Brain and Biological Neuron,
10-11 Model of an Artificial Neuron, Activation functions, Neural T1 (ch 1)
Network Architectures.
Single Layer Perceptron, Linear Separability, XOR Problem,
12-13 T1 (ch 3)
Perceptron Learning rules
Multilayer Perceptron, Back-propagation Algorithm and
14-16 T1 (ch 4)
parameters selection and tuning
Radial-Basis Function Networks, various kernel functions used
17-19 T1 (ch 5)
in RBFN
Autoencoder, Sparse autoencoder, Denoising autoencoder, Deep
20-24 R1
neural network based on stacking of autoencoders
25-27 Extreme learning machines, Kernel Extreme learning machine R4
Convolutional neural network, Convolutional
28-31 R2
Layer, Pooling Layer, and Fully-Connected Layer
Crisp Sets and Crisp relations, Fuzzy sets and Fuzzy relations,
32-34 T2 (ch 1)
Crisp Logic and Fuzzy Logic
Membership function, Fuzzification, Fuzzy Inference, T2 (ch4, ch5,
35-37
Defuzzification Methods, Applications of Fuzzy Logic ch9)
Neuro-Fuzzy System, Takagi-Sugeno’s Approach (ANFIS),
38-42 Fuzzy Backpropagation Networks, Advantages and Applications R5
of hybrid Neuro-Fuzzy Systems
5. Evaluation Scheme:
Durati Marks Nature of
Component Weightage (%) Date & Time
on Component
Mid-Sem Exam 90 min 20 % 60 -- Closed Book
Assignments and -------- 30% 90 -- Open Book
Programming Exercise
Comprehensive Exam 3 Hrs 50% 150 -- Closed Book
6. Chamber Consultation Hour: 3.30PM-4.30PM (Friday)
7. Notices: Notices concerning this course will be on CMS.
8. Make–up Examination: Make-up will be given on genuine grounds only. Prior application should be made
for seeking the make- up examination.
9. Academic Honesty and Integrity Policy: Academic honesty and integrity are to be maintained by all the
students throughout the semester and no type of academic dishonesty is acceptable.
Rajesh Kumar Tripathy
INSTRUCTOR-IN-CHARGE
