DEPARTMENT OF ARTIFICIAL INTELLIGENCE AND DATA SCIENCE

COURSE PLAN-INTEGRATED COURSE

Course Code CS3491

Artificial Intelligence and Machine
Course Name
Learning
Regulation 2021
Name of the Course Instructor(s) Mrs.A.Deepika, Ms.G.Aninthitha
Name of the Course Coordinator Mrs.A.Deepika
Academic Year: 2024-2025
CSE, CSE (CYBERSECURITY) /
Branch / Year / Semester
II/ IV
Date of Commencement of Class
Date of Completion of Class
Revision No 1

Prepared By, Verified By, Approved By,

Mrs.A.Deepika Dr.R.Deepalakshmi Dr.S.Durairaj
AP/CSE HoD-AIDS Principal

1
 SYLLABUS

COURSE
COURSE NAME L T P C
CODE
CS3491 Artificial Intelligence and Machine Learning 3 0 2 4
COURSE OBJECTIVES :
The main objectives of this course are to:
 Study about uninformed and heuristic search techniques.

 Learn techniques for reasoning under uncertainty

 Introduce Machine Learning and supervised learning algorithms

 Study about ensembling and unsupervised learning algorithms

 Learn the basics of deep learning using neural networks

UNIT I PROBLEM SOLVING 9

Introduction to AI - AI Applications - Problem solving agents – search algorithms – uninformed search strategies
– Heuristic search strategies – Local search and optimization problems – adversarial search – constraint
satisfaction problems (CSP)

UNIT II PROBABILISTIC REASONING 9

Acting under uncertainty – Bayesian inference – naïve bayes models. Probabilistic reasoning – Bayesian networks
– exact inference in BN – approximate inference in BN – causal networks.
UNIT III SUPERVISED LEARNING 9
Introduction to machine learning – Linear Regression Models: Least squares, single & multiple variables,
Bayesian linear regression, gradient descent, Linear Classification Models: Discriminant function – Probabilistic
discriminative model - Logistic regression, Probabilistic generative model – Naive Bayes, Maximum margin
classifier – Support vector machine, Decision Tree, Random forests

UNIT IV ENSEMBLE TECHNIQUES AND UNSUPERVISED LEARNING 9

Combining multiple learners: Model combination schemes, Voting, Ensemble Learning - bagging, boosting,
stacking, Unsupervised learning: K-means, Instance Based Learning: KNN, Gaussian mixture models and
Expectation maximization

UNIT V NEURAL NETWORKS 9

Perceptron - Multilayer perceptron, activation functions, network training – gradient descent optimization –
stochastic gradient descent, error backpropagation, from shallow networks to deep networks –Unit saturation (aka
the vanishing gradient problem) – ReLU, hyper parameter tuning, batch normalization, regularization, dropout.
TOTAL: 45 Periods

CONTENT BEYOND SYLLABI: Natural Language Processing

2
 PRACTICAL EXERCISES TOTAL: 30 Periods
1. Implementation of Uninformed search algorithms (BFS, DFS)
2. Implementation of Informed search algorithms (A*, memory-bounded A*)
3. Implement Naïve Bayes Models
4. Implement Bayesian Networks
5. Build Regression models
6. Build Decision Trees And Random Forests
7. Build SVM models
8. Implement ensembling techniques
9. Implement Clustering Algorithms
10. Implement EM for Bayesian networks
11. Build simple NN models
12. Build Deep Learning NN Models

COURSE OUTCOMES:
After the successful completion of this course, the student will be able to
CO1: Use appropriate search algorithms for problem solving
CO2: Apply reasoning under uncertainty
CO3: Build supervised learning models
CO4: Build ensembling and unsupervised models
CO5: Build deep learning neural network models

TEXT BOOKS:

T1: Stuart Russell and Peter Norvig, “Artificial Intelligence – A Modern Approach”, Fourth Edition,
Pearson Education, 2021.
T2: Ethem Alpaydin, “Introduction to Machine Learning”, MIT Press, Fourth Edition, 2020.

REFERENCE BOOKS/LINKS:

R1: Dan W. Patterson, “Introduction to Artificial Intelligence and Expert Systems”, Pearson Education,2007
R2: Kevin Night, Elaine Rich, and Nair B., “Artificial Intelligence”, McGraw Hill, 2008
R3: Patrick H. Winston, "Artificial Intelligence", Third Edition, Pearson Education, 2006
R4: Deepak Khemani, “Artificial Intelligence”, Tata McGraw Hill Education, 2013 (http://nptel.ac.in/)
R5: Christopher M. Bishop, “Pattern Recognition and Machine Learning”, Springer, 2006.
R6: Tom Mitchell, “Machine Learning”, McGraw Hill, 3rd Edition,1997.
R7: Charu C. Aggarwal, “Data Classification Algorithms and Applications”, CRC Press, 2014
R8: Mehryar Mohri, Afshin Rostamizadeh, Ameet Talwalkar, “Foundations of Machine Learning”, MIT Press, 2012.
R9: Ian Goodfellow, Yoshua Bengio, Aaron Courville, “Deep Learning”, MIT Press, 2016

3
 PLAN OF DELIVERY

Ref. Cumula Teaching

Sl. Teaching
Topic Covered Book Page No Hours tive Methodology (If
No Aid
Code Hours any)

UNIT-I PROBLEM SOLVING

T1 1-5
Introduction To AI – AI
1. 1 1 BB -
Applications R1 1-8
R2 4-8
Problem Solving Agents – T1 64-69
2. 1 2 BB+PPT -
Search Algorithms R2 25-36
Uninformed Search T1 81-91
3. 2 4 BB Think Pair Share
Strategies R3 64-69
T1 92-101
Heuristic Search
4. R2 50-70 2 6 BB -
Strategies
R3 70-75
Local Search And
5. T1 120-128 1 7 BB -
Optimization Problems
T1 161-180
6. Adversarial Search 1 8 BB -
R3 101-112
Constraint Satisfaction T1 202-222
7. 1 9 BB+PPT Think Pair Share
Problems (CSP) R4 353-370

UNIT-II PROBABILISTIC REASONING

T1 480-482
8. Acting Under Uncertainty 1 10 BB -
R4 864-869
9. Bayesian Inference T1 490-493 1 11 BB -
T1 495-498 BB
10. Naïve Bayes Models 1 12 Think Pair Share
R7 69-70 BB
11. Probabilistic Reasoning T1 510-512 1 13 BB -
T1 513-517
12. Bayesian Networks 2 15 BB+PPT -
R7 76-78
BB
13. Exact Inference In BN T1 522-529 1 16 -

Approximate Inference In T1 530-538 BB

14. 1 17 -
BN R5 461-473

4
 Ref. Cumula Teaching
Sl. Teaching
Topic Covered Book Page No Hours tive Methodology (If
No Aid
Code Hours any)

BB
15. Causal Networks - Notes 1 18 -

UNIT-III SUPERVISED LEARNING

Introduction To Machine
T2 1-4
Learning BB
16. 1 19 -
Linear Regression T2 36-38
Models R5 137-140
Least Squares, Single & BB
17. R5 184-186 1 20 -
Multiple Variables
Bayesian Linear R5 152-156
18. Regression, Gradient 1 21 BB Think Pair Share
R9 177-190
Descent
Linear Classification
19. Models: Discriminant R5 181-190 1 22 BB -
Function

20. Probabilistic R5 203-212 1 23 -

Discriminative Model BB
R5 217-218
21. Logistic Regression 1 24 BB+PPT -
R8 245-247
Probabilistic Generative R5 196-202
22. 1 25 BB -
Model – Naive Bayes R6 300-305
Maximum Margin T1 744-747
23. Classifier – Support 1 26 BB+PPT -
R8 63-75
Vector Machine

Decision Tree, T2 217-230

24. 1 27 BB -
Random Forests R7 493-495
UNIT-IV ENSEMBLE TECHNIQUES AND UNSUPERVISED LEARNING
Combining Multiple
25. Learners: Model R5 653-660 1 28 BB -
Combination Schemes

26. Voting R5 339-340 1 29 BB -

27. Ensemble Learning – R5 657-661 2 31 BB -

5
 Ref. Cumula Teaching
Sl. Teaching
Topic Covered Book Page No Hours tive Methodology (If
No Aid
Code Hours any)

Bagging, Boosting,
R7 491-498
Stacking

Unsupervised Learning:
28. T2 167-170 2 33 BB+PPT -
K-Means

Instance Based T2 194-196

29. 1 34 BB+PPT Think Pair Share
Learning: KNN R6 231-236
Gaussian Mixture Models T2 171-175
30. And Expectation 2 36 BB -
Maximization R6 191-195

UNIT-V NEURAL NETWORKS

Perceptron - Multilayer R6 86-88

31. 1 37 BB+PPT -
Perceptron
R7 14-15

32. Activation Functions R9 174-175 1 38 BB -

Network Training –
33. Gradient Descent R9 177-178 2 40 BB -
Optimization
Stochastic Gradient
34. R9 294-296 1 41 BB+PPT -
Descent
Error Backpropagation, R6 85-108
35. From Shallow Networks 1 42 BB -
To Deep Networks R9 204-220

Unit Saturation (Aka The

36. Vanishing Gradient R9 193-194 1 43 BB -
Problem) – Relu
37. Hyper parameter Tuning R9 428-430 1 44 BB Think Pair Share
Batch Normalization,
38. R9 258-268 1 45 BB -
Regularization, Dropout
Content Beyond Syllabus
Natural Language
39. Web reference 1 46 PPT -
Processing

6
 PLAN OF IMPLEMENTATION-Lab Experiments

Number of
Sl. Cumulative
List of Experiments periods Requirement
No periods
planned
Implementation of Uninformed search algorithms
4 4
1. (BFS, DFS)
Implementation of Informed search algorithms
4 8
2. (A*, memory-bounded A*)

Implement Naïve Bayes Models 2 10

3.
Implement Bayesian Networks 2 12
4.
Python 3.9 or
Build Regression models 2 14 later,
5.
Anaconda
Build Decision Trees And Random Forests 4 18 Distribution,
6.
python editors,
Build SVM models 2 20 Jupyter /
7.
PyCharm/
Implement ensembling techniques 2 22 equivalent
8.
Implement Clustering Algorithms 2 24
9.
2 26
10. Implement EM for Bayesian networks
2 28
11. Build simple NN models
2 30
12. Build Deep Learning NN Models

7
 ASSESSMENT PLAN

ASSESSMENT SCHEDULE-TEST

TEST DATE
TEST PORTION FOR TEST
NO. PLANNED CONDUCTED
Unit 1,2
Internal I
Assessment
Unit 3,4
Test II
Unit 1
Open Book I
Test Unit 3
II

ASSESSMENT SCHEDULE-ASSIGNMENT

Group Date of Submission

Assignment No Mode
/Common/Individual
I Written Group
II Seminar Individual

ASSESSMENT SCHEDULE-LABORATORY

DATE
PLANNED (HAS TO BE
MODEL TEST PORTION FOR TEST FILLED WITH RESPECT
CONDUCTED
TO THE ACADEMIC
CALENDAR)
All Experiments
I

ASSESSMENT PATTERN

ITEM WEIGHTAGE
Continuous Assessment-I 40
Internal Assessment Test – I 60
50%
Observation + Record 50
Model Lab 50
End Semester Examination

50%
Theory + Practical 100 + 100
(Theory 35% + Practical 15% )