TIET/CSE/CS3491/ AI&ML /II/IV
DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
COURSE PLAN
Name of the Faculty MRS .K. BAKYA
Designation/Department AP/CSE
Course Code/Name CS3491/ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING
Year/Sem/Department II/IV/BE (CSE)
Credits Details L:3 T:0 P:2 C:4
Total Contact Hours Required 45 + 30
Objective:
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.
Course outcomes (COs)
BLOOMS
CO DESCRIPTION TAXONOMY
LEVEL
Use appropriate search algorithms for problem Understand (K1)
CO1:
solving
CO 2: Apply reasoning under uncertainty Apply (K2)
CO 3: Build supervised learning models Apply (K3)
CO 4: Build ensembling and unsupervised models Evaluate (K4)
1
TIET/CSE/CS3491/ AI&ML /II/IV
CO 5: Build deep learning neural network models Apply (K5)
Course Outcome Vs Program Outcome Mapping:
CO PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12
CO 1 3 2 3 3 - - - - 1 3 3 3
CO 2 1 1 1 3 1 - - - 1 2 1 3
CO 3 2 1 2 1 1 - - - 2 1 1 3
CO 4 3 1 3 1 - - - - 2 1 2 1
CO 5 3 1 1 2 2 - - - 3 1 2 3
Syllabus:
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,
Probabilisticgenerativemodel–NaiveBayes,Maximummarginclassifier–
Supportvectormachine,DecisionTree,Randomforests.
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
2
TIET/CSE/CS3491/ AI&ML /II/IV
deep networks –Unit saturation (aka the vanishing gradient problem) – ReLU,
hyperparameter tuning, batch normalization, regularization, dropout.
Text Book:
[Link],“ArtificialIntelligence–AmodernApproach”,Fourth Edition, Pearson
Education, 2021.
[Link],“IntroductiontoMachineLearning”,MITPress,FourthEdition,2020.
REFERENCES:
[Link] W. Patterson, “Introduction to Artificial Intelligence and Expert Systems”,
PearsonEducation,2007
[Link],ElaineRich,andNairB.,“ArtificialIntelligence”,McGrawHill,2008
[Link],”ArtificialIntelligence”,ThirdEdition,PearsonEducation,2006
[Link],“PatternRecognitionandMachineLearning”,Springer,2006.
[Link],“MachineLearning”,McGrawHill,3rdEdition,1997.
[Link],“DataClassificationAlgorithmsandApplications”,CRCPress,2014
[Link],AfshinRostamizadeh,AmeetTalwalkar,“FoundationsofMachine Learning”, MIT
Press, 2012.
[Link],YoshuaBengio,AaronCourville,“DeepLearning”,MITPress,2016
Website:
Deepak Khemani, “Artificial Intelligence”, Tata McGraw Hill Education, 2013 ([Link]
Course Plan:
Topic Books for
Topic Teaching Proposed Completed BT
No. Reference CO
Tools Date Date Level
UNIT I PROBLEM SOLVING
Introduction to AI
1. T1 1 BB K1
AI Applications K1
2. T1 1 BB
Problem solving agents K1
3. T1 1 BB
search algorithms K1
4. T1 1 BB
K1
5. uninformed search strategies T1 1 BB
3
TIET/CSE/CS3491/ AI&ML /II/IV
Heuristic search strategies K1
6. T1 1 BB
Local search and optimization K1
7. T1 1 BB
problems
adversarial search K1
8. T1 1 BB
constraint
satisfaction K1
9. T1 1 BB
problems (CSP)
Implementation of Uninformed K1
10. T1 1 LAB
search algorithms (BFS, DFS)
Implementation of Uninformed K1
11. T1 1 LAB
search algorithms (BFS, DFS)
Implementation of Informed
search algorithms (A*, K1
12. T1 1 LAB
memory-bounded A*)
Implementation of Informed
search algorithms (A*, K1
13. T1 1 LAB
memory-bounded A*)
Implement naïve Bayes models K1
14. T1 LAB
Implement naïve Bayes models K1
15. T1 LAB
UNIT II PROBABILISTIC REASONING
Acting under uncertainty K2
1. T2 2 BB
Bayesian inference T2 K2
2. 2 BB
naïve bayes models T2 K2
3. 2 BB
Probabilistic reasoning T2 K2
4. 2 BB
Bayesian networks T2 K2
5. 2 BB
exact inference in BN T2 K2
6. 2 BB
approximate T2 K2
7. 2 BB
inference in BN T2 K2
8. 2 BB
causal networks.
9. T2 2 BB K2
Implement Bayesian Networks
10. T2 2 LAB K2
11. Implement Bayesian Networks T2 2 LAB K2
12. Build Regression models T2 2 LAB K2
4
TIET/CSE/CS3491/ AI&ML /II/IV
13. Build Regression models T2 2 LAB K2
Build decision trees and
14. T2 2 LAB K2
random forests
Build decision trees and
15. T2 2 LAB K2
random forests
UNIT III SUPERVISED LEARNING
Introduction to machine
1. T3 3 BB K3
learning
Linear Regression Models:
2. Least squares, single & multiple T3 3 BB K3
variables
Bayesian linear regression, T3
3. 3 BB K3
gradient descent
Linear Classification Models: T3
4. 3 BB K3
Discriminant function
Discriminant function – T3
5. Probabilistic discriminative 3 BB K3
model
- Logistic regression,
6. T3 3 BB K3
Probabilisticgenerativemodel
NaiveBayes,Maximummargincl
7. T3 3 BB K3
assifier
Support vector machine
8. T3 3 BB K3
DecisionTree,Randomforests
9. T3 3 BB K3
Build SVM models
10. T3 3 LAB K3
Build SVM models
11. T3 3 LAB K3
Implement ensembling
12. T3 3 LAB K3
techniques
Implement ensembling
13. T3 3 LAB K3
techniques
Implement clustering
14. T2 3 LAB K3
algorithms
Implement clustering
15. T2 3 LAB K3
algorithms
UNIT IV ENSEMBLE TECHNIQUES AND UNSUPERVISED LEARNING
1. Combining multiple learners T4 4 BB K4
2. Model combination schemes T4 4 BB K4
3. Voting, Ensemble Learning T4 4 BB K4
4. bagging, boosting, stacking T4 4 BB K4
5. Unsupervised learning: T4 4 BB K4
6. K-means T4 4 BB K4
5
TIET/CSE/CS3491/ AI&ML /II/IV
7. Instance Based Learning: KNN T4 4 BB K4
8. Gaussian mixture models T4 4 BB K4
9. Expectation maximization T4 4 BB K4
Implement EM for
10. Bayesian networks T4 4 LAB K4
Implement EM for Bayesian
11. T4 4 LAB K4
networks
13. Build simple NN models T4 4 LAB K4
14. Build simple NN models T4 4 LAB K4
15. Build simple NN models T4 4 LAB K4
UNIT V NEURALNETWORKS
Perceptron-Multilayer T5
1. 5 BB K5
perceptron
activation functions, network T5 K5
2. 5 BB
training
3. gradient descent optimization T5 5 BB K5
4. stochastic gradient descent T5 5 BB K5
error back propagation, from
5. shallow networks to deep T5 5 BB K5
networks
Unit saturation (aka the
6. vanishing gradient problem) T5 5 Internet K5
7. ReLU, hyperparameter tuning T5 5 Internet K5
8. Batch normalization, T5 5 Internet K5
9. Regularization, dropout T5 5 Internet K5
10. Build simple NN models T5 5 LAB K5
11. Build deep learning NN models T5 5 LAB K5
12. Build deep learning NN models T5 5 LAB K5
13. Build deep learning NN models T5 5 LAB K5
14. Build deep learning NN models T5 5 LAB K5
15 Build deep learning NN models T5 5 LAB K5
Assignment:
Mode of
Assign Batch Total Assignment
Register Number Topics
ment Details Number Written/
Seminar/PPT
I Batch – I 20 Written Problem solving agents
6
TIET/CSE/CS3491/ AI&ML /II/IV
causal networks
Batch – II 20 Seminar
Batch - III 20 PPT Bayesian networks
Linear Classification
Batch – I 20 Seminar Models: Discriminant
function
II Unsupervised learning:K
Batch – II 20 PPT
Means
Batch - III Written Gaussian mixture models
20
Batch – I Perceptron-Multilayer
20 PPT
perceptron
Unit saturation (aka the
III Batch – II 20 Written vanishing gradient
problem)
Batch - III 20 Seminar Batch normalization
Submission Details:
Phase 1(Before AT 1) Phase 2 (Before AT 2) Phase 3 (Before AT 3)
Assignment 1 UNIT-1&2 Assignment 2 UNIT-3&4 Assignment 3 UNIT-5
Prepared By (subject in charge) Verified By (HOD)
Approved By (IQAC) Verified By (PRINCIPAL)