SRM INSTITUTE OF SCIENCE AND TECHNOLOGY

FACULTY OF ENGINEERING AND TECHNOLOGY

SCHOOL OF COMPUTATIONAL INTELLIGENCE

COURSE PLAN
21AIC202J – NEURAL NETWORKS AND MACHINE
LEARNING

JANUARY – MAY 2025

Revision History:
Date Version Modification Modified by Reviewed by Authorized by
done
02-01-2025 1.0 Initial Release Dr. S. Abijah Roseline Dr. Annapurani
Panaiyappan K
SRM Institute of Science and Technology, Kattankulathur

Table of Contents

1.0 General Details............................................................................................................................ 3

2.0 Reference Books ......................................................................................................................... 3
3.0 Prerequisites ................................................................................................................................ 3
4.0 Instructional Objectives .............................................................................................................. 3
5.0 Overall Assessment Plan............................................................................................................. 4
6.0 Tentative Test Schedule .............................................................................................................. 4
7.0 Detailed Test Plan ....................................................................................................................... 5
8.0 Lab Experiments ......................................................................................................................... 6
9.0 Course Project Details................................................................................................................. 6
10.0 Assignment ................................................................................................................................. 7
11.0 Overall Execution Plan ............................................................................................................. 10

2
SRM Institute of Science and Technology, Kattankulathur

1.0 General Details

Course Code: 21AIC202J

Course Title: Neural Networks and Machine Learning

Semester: IV

Course Time: JANUARY – MAY 2025

Slot: D

Batch
Day Batch 1 Batch 2
Hour Timing Hour Timing
Day order 1 - - - -
Day order 2 - - - -
Day order 3 4 10:40 - 11:30 9 03:10 - 04:00
Day order 4 6,7 12:30 - 02:15 1,2 08:00 - 09:40
Day order 5 5 11:35 - 12:25 10 04:00 - 04:50

Location: Tech Park, Tech Park 2

Lab Hours: Batch 1: Day order 1 : 1st – 4th Hour
Batch 2: Day order 3 : 7th – 10th Hour

2.0 Reference Books

1. Christopher Bishop, “Pattern Recognition and Machine Learning” Springer, 2006
2. Kevin P. Murphy, “Machine Learning: A Probabilistic Perspective”, MIT Press, 2012
3. Ethem Alpaydin, “Introduction to Machine Learning”, Prentice Hall of India, 2005
4. Tom Mitchell, "Machine Learning", McGraw-Hill, 1997.
5. Hastie, Tibshirani, Friedman, “The Elements of Statistical Learning” (2nd ed)., Springer, 2008
6. Stephen Marsland, “Machine Learning –An Algorithmic Perspective”, CRC Press, 2009
7. Trevor Hastie, Robert Tibshirani, Jerome Friedman, h The Elements of Statistical Learning,
2nd edition, springer series in statistics.
8. Ethem Alpaydın, Introduction to machine learning, second edition, MIT press.

3.0 Prerequisites
Nil

4.0 Instructional Objectives

1. To recognize the basics of learning problems

2. To illustrate the decision tree algorithm for classification and prediction

3. To identify the probability based and instance-based learning methods to solve the real-world
problems
3
SRM Institute of Science and Technology, Kattankulathur

4. To express the perception of neurons and network functioning

5. To demonstrate the working NN models to solve real world problems

5.0 Overall Assessment Plan

# Component Type Marks

1 FJ-I Written Test 10

Higher Order Assignment - 1 5

2 FJ-II Scenario-based Assessment 6

Group Activity 6

Application Review - 2 3

3 FJ-III MCQ based Assessment 5

Application Development 10
(Demo/Analytical Summary)
4 LLJ-I Lab Experiment (1-7) 4

Application Review - 1 3
5 LLJ-II Lab Experiment (8-15) 4
Practical Test 4
Total Marks 60
INTERNAL END SEMESTER EXAM TOTAL
(THEORY) (THEORY)

60 Marks 40 Marks 100 Marks

6.0 Tentative Test Schedule

# Tentative date Test Marks Portion Duration

10 Unit 1 &
1 1st week of Cycle Test - I 100 minutes
2
March
6 Unit 3
2 3rd week of Scenario-based 50 minutes
&4
April Assessment

3 1st week of May MCQ based Assessment 5 Unit 5 50 minutes

4
SRM Institute of Science and Technology, Kattankulathur

7.0 Detailed Test Plan

Cycle Test-1:
Portion : UNIT−1 & UNIT−2
Question Paper Pattern:
Description Question Type Number of Choice Marks
Questions (YES/NO)
PART−A MCQ 10 No 1*10= 10 Marks
PART−B Descriptive Type 4 Yes 5*4 = 20 Marks
PART−C Descriptive Type 2 Either Or 10*2= 20 Marks
Total Marks : 50 Marks
Internal Marks : 10 Marks
Blooms Level to be followed :
L1 (Remembering) - 40%
L2(Understanding) - 40%
L3 (Apply) - 20%

Scenario-based Assessment:
Portion : UNIT−3 & UNIT−4
Question Paper Pattern:
Description Question Type Number of Choice Marks
Questions (YES/NO)
PART−A Descriptive Type 2 Either Or 2*10 = 20 Marks
Total Marks : 20 Marks
Internal Marks : 6 Marks
Blooms Level to be followed :
L2(Understanding) - 30%
L3 (Apply) - 70%

MCQ based Assessment

Portion : UNIT−5
Question Paper Pattern:
Description Question Type Number of Choice Marks
Questions (YES/NO)
PART−A MCQ 20 No 1*20 = 20 Marks
Total Marks : 20 Marks
Internal Marks : 5 Marks
Blooms Level to be followed :
L1 (Remembering) - 40%
L2(Understanding) - 50%

5
SRM Institute of Science and Technology, Kattankulathur

8.0 Lab Experiments

Description Split up Marks Total Marks

Lab Code
Experiments 4 Marks 10 Marks
Execution 3 Marks
Viva 3 Marks

Internal Marks : 12 Marks

Average of 1-7 experiments – 4 marks
Average of 8-15 experiments – 4 marks
Practical Test – 4 marks

List of experiments:
Lab 1: Water jug problem
Lab 2: FIND-S algorithm
Lab 3: Candidate Elimination
Lab 4: Decision tree based ID3 algorithm
Lab 5: Naïve Bayesian classifier
Lab 6: Linear Regression
Lab 7: Logic Regression
Lab 8: Single Layer perceptron
Lab 9: Multi-Layer Perceptron
Lab 10: Backpropagation
Lab 11: KNN classifier
Lab 12: Clustering using k-Means
Lab 13: EM for clustering
Lab 14: Training SVM classifier
Lab 15: Feature Extraction by PCA

9.0 Application Review Details

Description Split up Marks Total Marks

Project Application Review- 3 Marks

1 16 Marks
Application Review- 3 Marks
2
Final Presentation 2 Marks
Demo 5 Marks
Analytical Summary 3 Marks
Internal Marks : 16 Marks

6
 SRM Institute of Science and Technology, Kattankulathur

10.0 Assignment
Description Marks Total Marks

Higher Order Assignment 5 Marks 5 Marks

Internal Marks : 5 Marks

11.0 Detailed Session Plan

Method of
Learning
Module delivery Take home
Week Major Topic materials to
/ Unit (Multi- Assignment(s)
be referred
Select)
Basics of Learning, Introduction to
Machine Learning, well posed
2.4
learning problems, designing a
1 Learning system 1 Lecture
Perspectives in Machine Learning,
Issues in Machine Learning,
2.4
Concept learning task, Concept
2 learning as search 1 Lecture
Find-S algorithm, Version space,
Candidate Elimination algorithm, 2.4
3 Inductive Bias 1 Lecture
Introduction to Decision Tree,
Decision tree representation,
Decision Tree Learning, 2.4
Appropriate problems for decision
4 tree learning 2 Lecture
Basic decision tree learning
algorithm, ID3, Entropy and 2.4
5 Information gain 2 Lecture
Hypothesis space search in
decision tree learning, Inductive
2.4
bias in decision tree learning,
6 Issues in decision tree learning 2 Lecture Assignment
Introduction to Bayesian Learning,
Naive Bayes classifier, Bayesian 2.4
belief networks, EM algorithm
7 3 Lecture
Instance Based Learning,
Introduction to k-nearest neighbour 2.4
8 learning, case-based reasoning 3 Lecture
SVM classifier,
Maximum margin linear
separators, Quadratic
2.4
programming solution to finding
maximum margin separators,
9 Kernels for learning, non-linear 3 Lecture

7
 SRM Institute of Science and Technology, Kattankulathur

functions, PCA, Covariance,

Correlation

Introduction to Neurons, biological

motivation, Neural Networks, 2.4
10 Neuron Modelling 4 Lecture
Linear threshold units, Perceptron,
Representational limitation, 2.1
11 gradient descent training 4 Lecture
Stochastic Gradient Descent, 2.1
Linear
regression, Logic Regression,
12 locally weighted regression 4 Lecture
2.1
Multilayer networks, Hidden layers,
Error Calculation Functions,
Different Activation Functions
13 5 Lecture
Backpropagation, constructing 2.1
intermediate representations,
Distributed representations, Flipped mode
14 Overfitting 5 Discussion
Learning network structure, 2.1
Recurrent networks, Convolution
Neural Networks, ReLu, Pooling,
SoftMax, Long Short-Term Flipped mode
15 Memory (LSTM) 5 Discussion

12.0 Overall Execution Plan:

Assigned
# Activity Target Dates Responsibilities to

Content All
1 02-01-2025 Develop a content outline or structure based on the objectives
Preparation faculties

1. Prepare lab programs for the topic assigned.

Lab Program 2. Questions have to be framed on their own and not to be taken
Exercises as such from any other source. Other sources can be referred to, All
2 06-01-2025
Questions but the question has to be modified with different example faculties
Preparation programs, and so on.
3. A solution is required for all the questions.

1. Questions have to be framed on their own and not to be taken

as such from any other source. Other sources can be referred to,
but the question has to be modified with different example
Question Bank programs, and so on. All
3 17-02-2025
Preparation 2. A solution is required for all questions. faculties
Multiple Choice Questions - 5
Concept Understanding Questions - 2
Scenario-based / HOTs Questions - 1

8
 SRM Institute of Science and Technology, Kattankulathur

1. Check for the quality of the questions as per the category in

21-02-2025
Question Bank the question bank. All
4 17-03-2025
Scrutiny 2. Ensure there are no repetitions. faculties
23-04-2025
3. Coordinate with CC.

1. Select the question from Question Bank

28-02-2025
2. Share the QP to audit professor for review All
5 Cycle Test 19-03-2025
3. Plan for cycle tests question paper printing, print, and faculties
01-05-2025
distribute.
4. Coordinate with CC.

1. Responsible for the preparation of course files as per the

checklist.
2. At the end of each CT exam, files should be updated and
10-03-2025
verified by the Team Head.
Course File 02-04-2025 All
6 3. Participate in result analysis activity.
Preparation 12-05-2025 faculties
4. Course Files are to be prepared for each department and the
23-05-2025
faculties listed are responsible for the preparation including CO-
PO Mapping, attainment of Cos, etc.
5. Coordinate with CC.

07-02-2025
1. Team head of each unit along with the team to prepare
17-02-2025
questions for quiz/puzzle/review for each unit with a solution. All
7 Review questions 03-03-2025
2. Share to CC for review. faculties
12-03-2025
3. Share the reviewed questions to all faculties.
22-04-2025

17-02-2025
Feedback 1. Scribe and prepare minutes of meetings for all meetings
09-03-2025
Collection and conducted. All
8 02-04-2025
Minutes of 2. Share the MoM with CC and Audit professors on the same day faculties
16-04-2025
Meeting or the next meeting.
13-05-2025