Syllabus MTech AI

SVKM’s NMIMS
Mukesh Patel School of Technology Management & Engineering
Program: M. Tech Artificial Intelligence Semester: I

Course/Module : An introduction to Artificial Module Code: MTAI01001
Intelligence and AI framework
Teaching Scheme Evaluation Scheme
Lecture Practical Tutorial Internal Continuous Term End
(Hours (Hours (Hours Assessment Examinations (TEE)
Credit
per per per (ICA) (Marks -100 in
week) week) week) (Marks -50) Question Paper)
4 0 0 4 Scaled to 50 Marks Scaled to 50 marks

Pre-requisite: Students are required to have the following prerequisites:
• Linear algebra (vectors, matrices, derivatives)
• Basic probability theory
• Python programming
Objectives:
 Understanding of learning agent
 Programming for breadth first and depth first search for visiting all possible solution
and picking up the most optimum solution
 Information gathering from data for decision making
Course Outcomes:
After completion of the course, students would be able to :
We will provide a broad understanding of the basic techniques for building intelligent
computer systems. Topics include the history of AI, intelligent agents, state-space problem
representations, uninformed and heuristic search, game playing and adversarial search, logical
agents, constraint satisfaction problems, along with techniques in machine learning and other
applications of AI, such as natural language processing (NLP).
Detailed Syllabus: (per session plan)
Unit Description Duration
1. Introduction to AI, history of AI, course logistics, and roadmap 10
Intelligent agents, uninformed search
2. Heuristic search, greedy search, A* algorithm, stochastic search 10
Adversarial search, game playing
3. Machine Learning 1: basic concepts, linear models, K nearest 12
neighbors, over-fitting
Machine Learning 2: perceptrons, neural networks, naive Bayes
4. Machine Learning 3: Decision trees, ensemble, logistic regression, 12
and unsupervised learning
Constraint satisfaction problems
___________ ____________
Signature Signature
(Prepared by Concerned Faculty/HOD) (Approved by Dean)
M. TECH /AI/2020-21/SEM I /Page 1 of 10

SVKM’s NMIMS
5. Markov decision processes, reinforcement learning. 12

Logical agents, propositional logic and first order logic
6. AI applications to natural language processing (NLP) 04

AI applications and course review
Total 60
Text Books:
1. Artificial Intelligence A Modern Approach - Stuart J. Russell , Peter Norvig, Pearson
Education, 2011
2. Nils Nilsson, Artificial Intelligence: A New Synthesis, Morgan Kaufmann, 1998.
3. David Poole, Alan Mackworth, Artificial Intelligence: Foundations for Computational
Agents, Cambridge Univ. Press, 2010.
Reference Books:
1. Artificial Intelligence, Structures and Strategies for Complex Problem Solving, George F
Luger, Pearson Education 2009
2. Ronald Brachman, Knowledge Representation and Reasoning, Morgan Kaufmann, 2004.
3. Frank van Harmelen, Vladimir Lifschitz, Bruce Porter (Eds), Handbook of Knowledge
Representation, Elsevier, 2008.
4. Ivan Bratko, Prolog Programming for Artificial Intelligence, 4th Ed., Addison-Wesley, 2011.
5. Stephen Marsland, Machine Learning: An Algorithmic Perspective, Chapman and Hall,
2009.
6. Christopher Bishop, Pattern Recognition and Machine Learning, Springer, 2007
Any other information: NIL
Total Marks of Internal Continuous Assessment (ICA): 50 Marks
Distribution of ICA Marks:
Description of ICA Marks

Test Marks 20
Term Work Marks 30
Total Marks : 50
Details of Term work:

 Minimum 5 practical experiments covering all the topics.
 Minimum two Assignments.
 Two class tests.
___________ ____________
Signature Signature

SVKM’s NMIMS
Program: M. Tech Artificial Intelligence Semester : I

Course/Module : Statistical Learning Module Code :MTAI01002
Lecture Practical Tutorial Internal Continuous Term End Examinations
(Hours (Hours (Hours Assessment (TEE)
Credit
per per per (ICA) (Marks -100 in Question
week) week) week) (Marks -50) Paper)
Pre-requisite: Nil
Objectives:
• To provide advanced statistical background for analyzing data and drawing inferences from
that analysis
• Predicative Analytics using liner and generalized liner model
Outcomes:
 Students will be able to learn advanced statistical technique and apply them to the analysis
of real data sets from different fields.
1 Descriptive Statistics:
a) Measures of Central Tendencies – Grouped and Ungrouped Data; Mean, 4
Sample Mean – Weighted mean; Median , Quartiles
b) Deciles, and Percentiles, Box plot, Mode, Measures of Variability –
Dispersion, Range, Standard deviation, Population v/s sample variance and
standard deviation, Skewness, Kurtosis.
Introduction to Probability and Sampling distribution:
a) Methods of Assigning probabilities, Probability Space, conditions of
probability model, Events, simple and compound, Laws of probability,
Probability density function, Cumulative distribution function, Expected
values of Mean and Variance. Marginal , union, joint and conditional 8
probabilities, Bayes’ Theorem
2
b) Random variables, discrete and continuous distributions, Expectation, 8
moments of a distribution, Binomial, Poisson, uniform, and normal
distributions, Normal approximation to the binomial distribution,
Distributions of several random variables, moments of joint distributions,
independence, covariance, correlation coefficient, Central Limit Theorem
___________ ____________
Signature Signature

SVKM’s NMIMS
Hypothesis Testing:
a) Large Sample estimation of the population parameters and Hypothesis
testing: Basics of Estimating the populations mean and difference; estimating
6
the proportion and difference; large sample test for population mean,
difference; large sample test for proportion, difference.
3 6
b) Estimation of a population variance: Sampling distribution of variance,
estimation.
6
c) Inferences from small sample: Student’s t distribution; Small sample t test
for following – A population mean, A difference between two means,
Confidence interval.
Regression Model:
a) least squares and linear regression: Introduction; Notation; Ordinary least
squares; Regression to the mean; Linear regression; Residuals; Regression
inference 6
4 b) Multivariable regression: Multivariate regression; Multivariate examples;
Adjustment; Residual variation and diagnostics; Multiple variables , 4
Interaction Terms, Non-linear Transformations of the Predictors, Qualitative
Predictors
Generalized linear models:
Logistic Regression, Binary outcomes, Count outcomes,
Multiple Logistic Regression 4
5 ANOVA/MANOVA: Chi-Square and Analysis of Variance, Multivariate 4
analysis of variance 4
Extension of regression analysis: Ridge Regression, The Lasso
Total 60
Text Books:
1. An Introduction to Statistical learning with application in R . Hastie T, Robert T. (2014).
Springer Science Business Media: New York
Reference Books:
1. Statistics for Management, Seventh Edition, by Richard I. Levin, David S. Rubin, Pearson
2. An Introduction to Categorical Data Analysis. Agresti, A. (2012). John Wiley & sons
3. The Element of Statistical Learning, Data mining, Inference and Prediction. Hastie, T,
Tibshirani, R, & Friedman, J. (2011). New York: Springer Series in Statistics.
4. Hair, Black, Babin, Anderson and Tatham (2009). Multivariate Data Analysis, Pearson
___________ ____________
Signature Signature

SVKM’s NMIMS

Test Marks 20
Term Work Marks 30
Total Marks : 50

• Practical based on 10 Experiments
• Two class tests.
• Minimum two assignments
___________ ____________
Signature Signature

SVKM’s NMIMS
Program: M. Tech Artificial Intelligence Semester: I

Course: Computer Vision Module Code: MTAI01003
Internal
Lecture Practical Tutorial Term End
Continuous
(Hours per (Hours per (Hours per Credit Examinations (TEE)
Assessment
week) week) week) (Marks -100
(ICA)
in Question Paper)
(Marks -50)
Pre requisite: Nil
Objectives:
Computer Vision focuses on the development of algorithms and techniques to analyse and
interpret the visible world around us. This requires understanding of the fundamental concepts
related to multi-dimensional signal processing, feature extraction, pattern analysis, visual
geometric modelling, stochastic optimization etc. Knowledge of these concepts is necessary in
this field, to explore and contribute to research and further developments in the field of
computer vision. Applications range from Biometrics, Medical diagnosis, document
processing, mining of visual content, to surveillance, advanced rendering etc.
Outcomes:
• The theoretical and practical aspects of computing with images
• Understand the geometric relationship between 2D images and the 3D world.
Detailed Syllabus: (Per Session Plan)
Digital Image Formation and low-level processing: Overview and
State-of-the-art, Fundamentals of Image Formation, Transformation:
1 Orthogonal, Euclidean, Affine, Projective, etc; Fourier Transform, 08
Convolution and Filtering, Image Enhancement, Restoration,
Histogram Processing.
Depth estimation and Multi-camera views: Perspective, Binocular
2 Stereopsis: Camera and Epipolar Geometry; Homography, 08
Rectification, DLT, RANSAC, 3-D reconstruction framework; Auto-
calibration. Apparel
Feature Extraction: Edges - Canny, LOG, DOG; Line detectors
(Hough Transform), Corners - Harris and Hessian Affine,
3 Orientation Histogram, SIFT, SURF, HOG, GLOH, Scale-Space 10
Analysis- Image Pyramids and Gaussian derivative filters, Gabor
Filters and DWT.
Image Segmentation:Region Growing, Edge Based approaches to
4 segmentation, Graph-Cut, Mean-Shift, MRFs, Texture 08
Segmentation; Object detection. 08
___________ ____________
Signature Signature

SVKM’s NMIMS
Pattern Analysis : Clustering: K-Means, K-Medoids, Mixture of

Gaussians, Classification: Discriminant Function, Supervised, Un-
5 supervised, Semi-supervised; Classifiers: Bayes, KNN, ANN 10
models; Dimensionality Reduction: PCA, LDA, ICA; Non-
parametric methods.
Motion Analysis: Background Subtraction and Modeling, Optical
6 Flow, KLT, Spatio-Temporal Analysis, Dynamic Stereo; Motion 08
parameter estimation.
Shape from X :Light at Surfaces; Phong Model; Reflectance Map;
7 Albedo estimation; Photometric Stereo; Use of Surface Smoothness 08
Constraint; Shape from Texture, color, motion and edges.
Total 60 hours
Text Books:
1. Richard Szeliski, Computer Vision: Algorithms and Applications, Springer-Verlag London
Limited 2011
2. Computer Vision: A Modern Approach, D. A. Forsyth, J. Ponce, Pearson Education, 2003.
Reference Books:
1. Richard Hartley and Andrew Zisserman, Multiple View Geometry in Computer Vision,
Second Edition, Cambridge University Press, March 2004
2. K. Fukunaga; Introduction to Statistical Pattern Recognition, Second Edition, Academic
Press, Morgan Kaufmann, 1990.
3. R.C. Gonzalez and R.E. Woods, Digital Image Processing, Addison- Wesley, 1992.

Test Marks 20
Term Work Marks 30
Total Marks : 50

 Practical based on 10 Experiments
 Two class tests.
 Minimum two assignments
___________ ____________
Signature Signature

SVKM’s NMIMS
Program: M. Tech Artificial Intelligence Semester : I

Course/Module : Machine Learning Module Code : MTAI01004
Lecture Practical Tutorial Internal Continuous Term End Examinations
(Hours (Hours (Hours Assessment (TEE)
Credit
per per per (ICA) (Marks -100 in Question
week) week) week) (Marks -50) Paper)
Pre-requisite: Statistical Learning
Objectives:
• To introduce and provide some core and necessary data mining techniques so that students
understand how to work with large data sets and apply the appropriate data mining
technique to answer business questions
Outcomes:
• Students will able to learn a number of well-defined data mining tasks such as
classification, estimation, prediction, affinity grouping and clustering, and data
visualization are discussed
Resampling Methods: Cross-Validation, Bootstrap, Cross-Validation
1 10
and the Bootstrap, k-Fold Cross-Validation
Linear Model Selection and Regularization: Subset Selection,
Shrinkage Methods, Ridge Regression, Lasso, Selecting the Tuning
2 10
Parameter, Dimension Reduction Methods, Principal Components
Regression, Partial Least Squares, PCR and PLS Regression
Moving Beyond Linearity: Polynomial Regression, Step Functions, 10
3 Basis Functions, Regression Splines, Smoothing Splines, Local
Regression, Generalized Additive Models, Non-linear Modeling, GAMs
Tree-Based Methods: The Basics of Decision Trees, Regression Trees,
4 Classification Trees, Trees Versus Linear Models, Advantages and 10
Disadvantages of Trees, Bagging, Random Forests, Boosting,
Support Vector Machines: Maximal Margin Classifier, Support Vector
Classifiers, Support Vector Machines, SVMs with More than Two
5 10
Classes, Relationship to Logistic Regression, ROC Curves, Application
to Gene Expression Data
Unsupervised Learning: The Challenge of Unsupervised Learning,
Principal Components Analysis, Clustering Methods, K-Means
6 10
Clustering, Hierarchical Clustering, Practical Issues in Clustering,
NCI60 Data Example and PCA on this dataset
___________ ____________
Signature Signature

SVKM’s NMIMS
Total 60
Text Books:
1. An Introduction to Statistical learning with application in R . Hastie T, Robert T. (2014).
Springer Science Business Media: New York
2. Hair, Black, Babin, Anderson and Tatham (2009). Multivariate Data Analysis, Pearson
Reference Books:
1. Statistics for Management, Seventh Edition, by Richard I. Levin, David S. Rubin, Pearson
2. An Introduction to Categorical Data Analysis. Agresti, A. (2012). John Wiley & sons
3. The Element of Statistical Learning, Data mining, Inference and Prediction. Hastie, T,
Tibshirani, R, & Friedman, J. (2011). New York: Springer Series in Statistics.
4. Gujarati, Damodar N, and Dawn C. Porter. Basic Econometrics. Boston, Mass: McGraw-
Hill, 2009

Test Marks 20
Term Work Marks 30
Total Marks : 50

1. Practical based on 10 Experiments
2. Two class tests.
3. Minimum two assignments
___________ ____________
Signature Signature

SVKM’s NMIMS
Program: M. Tech. – Artificial Intelligence Semester: I

Course/Module : Research Project – I Module Code: MTAI01007
Internal Continuous Term End
Lecture Practical Tutorial
Assessment Examinations (TEE)
(Hours per (Hours per (Hours per Credit
(ICA) (Marks --
week) week) week)
(Marks -50) in Question Paper)
0 4 0 2 Scaled to 50 marks -
Pre-requisite: Nil
Objectives:
 Apply all learning in this semester and work on a topic of research leading to a paper in
journal or seminar.
Outcomes:
After completion of the course, students would be able to:
 Learn research methodology
 Write a technical paper
1 Select a topic of research 04
2 Paper review 15
3 Make a strategy to work on a project (subject finalization) 15
4 Actual research 20
5. Finalization of paper for publication 06
Total 60
Text Books:
1. Research methodology
2. Actual paper reading

Test Marks --
Term Work Marks 50
Total Marks : 50
Details of Term work: As per institute norms
___________ ____________
Signature Signature

SVKM’s NMIMS
Program: M. Tech Artificial Intelligence Semester: II

Course/Module: Natural Language Processing Module Code: MTAI02001
Internal Continuous Term End
Assessment Examinations (TEE)
(Hours (Hours (Hours Credit (Marks -100
(ICA)
per week) per week) per week) (Marks -50) in Question
Paper)
Pre-requisite:
Students are required to have the following prerequisites:
 Basic probability and statistics
 Programming
Objectives:
 Understanding biology of Natural Language Processing; Place and Manner of
Articulation; Word Boundary Detection; Argmax based computations;
 Morphology fundamentals; Morphological Diversity of Indian Languages;
Morphology Paradigms; Finite State Machine Based Morphology; Automatic
Morphology Learning; Shallow Parsing; Named Entities; Maximum Entropy
Models; Random Fields.
Course Outcomes:
This course will examine the state-of-the-art in applied NLP, with an emphasis on
how well the algorithms work and how they can be used (or not) in
applications. Today there are many ready-to-use plug-and-play software tools for
NLP algorithms. For this reason, this course will emphasize getting facile with quick
programs using existing tools. The intended learning outcomes are for students to:
1. Learn about major NLP issues and solutions
2. Become agile with NLP programming
3. Be able to asses NLP problems
4. Be able to get the gist of relevant research papers
5. Understand Natural language understanding, processing, generation.
Detailed Syllabus:
1. Introduction, Machine Learning and NLP, ArgMax 06
Computation, Syntactic Collocations; More on Term Weighting
2. Practice with ipython Notebooks, NLTK Text; Adopt a text 06
collection, Tokenize Your Text Collection, Create a First Look at
Your Text Collection, Parts of Speech and Tagging, Part of
___________ ____________
Signature Signature
M. TECH /AI/2020-21/SEM II /Page 1 of 13

SVKM’s NMIMS
Speech Tagging, POS Taggers, Practice Training a POS Tagger,

Chunking
WSD : WordNet, Wordnet; Application in Query Expansion,
Wiktionary; semantic relatedness, Measures of WordNet
Similarity, Similarity Measures (contd.), Resnick's work on
WordNet Similarity
3. WordNet Lexical Relations, Work on your Keyphrase 06
assignment, Keyphrase Identification Assignment, Run
Keyphrase Extraction on Mystery Text,
Names features
Parsing Algorithms, Evidence for Deeper Structure; Top Down
Parsing Algorithms, Noun Structure; Top Down Parsing
Algorithms- contd, Non-noun Structure and Parsing Algorithms
4. Probabilistic parsing; sequence labeling, PCFG, Probabilistic 06
parsing; PCFG (contd.), Probabilistic parsing: Training issues
Pandas Intro and Readings, Read About Syntactic and Semantic
Parsing
Review, Parsing, and Logic, Kaggle-based Text Classification
Assignment
5. Arguments and Adjuncts, Probabilistic parsing; inside-outside 06
probabilities
Text Clustering, Distributional Semantics readings, Clustering
and Distributional Semantics
6. Morphology, Graphical Models for Sequence Labelling in NLP, 04
Graphical Models for Sequence Labelling in NLP (contd.)
7. Phonetics, Consonants (place and manner of articulation) and 04
Vowels
Vowels (contd.), Forward Backward probability; Viterbi
Algorithm
8. Phonology, Sentiment Analysis and Opinions on the Web, 04
Machine Translation and MT Tools - GIZA++ and Moses.
9. Text Entailment, POS Tagging., Phonology; ASR 04
10. HMM and Viterbi, HMM and Viterbi (contd) 04
___________ ____________
Signature Signature

SVKM’s NMIMS
11. Precision, Recall, F-score, Map, Semantic Relations; UNL; 05

Towards Dependency Parsing., Universal Networking
Language
12. Semantic Role Extraction, Baum Welch Algorithm; HMM 05
training, Baum Welch Algorithm; HMM training
Total 60
Text Books:
1. Natural Language Processing with Python online book:
http://www.nltk.org/book/
2. Speech and Language Processing, 2nd Edition 2nd Edition by Daniel Jurafsky,
James H. Martin
Reference Books:
1. Natural Language Processing with Python: Analyzing Text with the Natural
Language Toolkit 1st Edition by Steven Bird, Ewan Klein, Edward Loper
2. Applied Text Analysis with Python: Enabling Language-Aware Data Products with
Machine Learning 1st Edition by Benjamin Bengfort, Rebecca Bilbro, Tony Ojeda
3. Natural Language Processing and Computational Linguistics: A practical guide to
text analysis with Python, Gensim, spaCy, and Keras Paperback – June 29, 2018 by
Bhargav Srivinasa-Desikan
Details of Internal Continuous Assessment (ICA):

Test Marks: 20
Term Work Marks: 30

1. Minimum two Assignments.
2. Two class tests.
___________ ____________
Signature Signature

SVKM’s NMIMS

Course/Module: Robotics and Automation Module Code: MTAI02002
Tutorial Internal Continuous Term End
Lecture Practical
(Hours Assessment Examinations (TEE)
(Hours per (Hours Credit (Marks -100
per (ICA)
week) per week) (Marks -50) in Question
week)
Paper)
Scaled to 50
4 0 0 4 Scaled to 50 Marks
marks
Pre-requisite: Linear Algebra, Vector and Matrix
Objectives:
1. To provide knowledge to students with the concept and techniques in rob
manipulator control
2. To expose students to evaluate, choose and incorporate robots in engine systems
and programming of robots
3. To understand and analyse various applications of robots
Course Outcomes:
1. Know the basics of Robots
2. Apply the knowledge of vector mathematics and geometry for kinem (direct and
inverse) motion
3. Perform trajectory planning and work space analysis for robots
4. Use image representation for robots movement
5. Perform autonomous mobile robot kinematics
Detailed Syllabus:
1. Basic concept in Robotics: Introduction, advantage and 07
applications of robots, automation of robots, non-
industrial applications, basic structures of robots,
numerical control of machine tools, resolution, accuracy
and repeatability, position representation, point to point
continuous path systems, point to point robotic system,
continuous – path robotic system, control loop of Robotic
systems, the manipulator, Cartesian coordinate robots,
cylindrical coordinate robots, spherical coordinate robots,
articulated robots
2. Kinematic Analytics & Coordinate Transformation: 08
Direct kinematic problem in robotics, geometry based
direct kinematics Analysis coordinate & vector
___________ ____________
Signature Signature

SVKM’s NMIMS
transformation using matrices, the orientation matrix &

translator vector, homogeneous transformations, Denavit
Hartenberg convention – implementing the DH
convention, obtaining the DH displacement matrices,
application of DH method- three axis robot arms, three
axis wrist, six axis robots manipulations, assigning the tool
coordinate system
3. Inverse Kinematics: General properties of solution, tool 08
configuration vector for: Two axes planar articulated robot
arm, three axis robots, four axis robots and five axis robots,
inverse kinematics analysis of two axes planar articulated
robot arm, three axis robot and four axis robots
4. Workspace analysis and trajectory planning or robots: 07
Robot work space envelops and examples, detail work
space analysis of two axis planar articulated robot arm,
four axis robots, different type of motions such as pick and
place motions, continuous path motion, interpolation
motion, straight line motion, workspace fixture
5. Robot Vision: Image representation and analysis, 08
template matching, polyhedral objects, shape analysis,
segmentation (thresholding, region labelling), iterative
processing, perspective transformation, structuring
illumination, camera motion
6. Task Planning: Task planner, task level programming, 07
uncertainty, configuration, space, gross motion, planning,
grasp planning, fine-motion, simulation of planar motion
7. Autonomous mobile Robots: Introduction, locomotion – 10
key issues of locomotion, legged mobile robots, leg
configuration and stability, examples of legged robot
locomotion, wheeled mobile robots, wheeled locomotion –
the design space, wheeled locomotion: case study
8. Application of AI on Robotics (also robotics on AI) 5
Total 60
Text Books:
 Fu, Gonzales and Lee, Robotics – Control, Sensing, Vision and Intelligence,
McGraw Hill. 1st Edition, 2008
 Robert Schilling, Fundamentals of Robotics – Analysis and control, Prentice Hall
of India, 1990 (classic)
Reference Books:
1. JJ Craig, Introcution to Robotics, Pearson Education. 8th edition, 2004
___________ ____________
Signature Signature

SVKM’s NMIMS
2. Ronald Siegwart & Illah R Nourbaksh, Introduction to autonomous mobile Robots,

EEE ed PHI 2004
3. Mittal and Nagrath, Robotics and Control, Tata McGraw Hill, 3rd edition, 2003

Test Marks: 20
Term Work Marks: 30

2. Two class tests.
Program: M. Tech. Artificial Intelligence Semester : II
___________ ____________
Signature Signature

SVKM’s NMIMS
Course/Module: Advanced Statistical Learning Module Code : MTAI02003

Practical Tutorial Internal Continuous Term End
Lecture
(Hours (Hours Assessment Examinations (TEE)
(Hours Credit
per per (ICA) (Marks -100
per week) (Marks -50)
week) week) in Question Paper)
Pre-requisite: Statistical learning
Objectives:
 To introduce and provide some core and necessary data mining techniques so that
students understand how to work with large data sets and apply the appropriate
data mining technique to answer business questions
Outcomes:
 Students will able to learn a number of well-defined data mining tasks such as
classification, estimation, prediction, affinity grouping and clustering, and data
visualization are discussed
Detailed Syllabus:
ANOVA/MANOVA:
1 Chi-Square and Analysis of Variance, Multivariate analysis of 6
variance
Extension of regression analysis:
2 4
Ridge Regression, The Lasso
Multivariate Analysis:
a) Canonical Analysis, Canonical Roots/Variates
b) Using Bayes’ Theorem for Classification, Procedure of
Discriminant Analysis, Linear Discriminant Analysis, Estimating
6
Misclassification, Probabilities, Quadratic Discriminant Analysis
8
c) Conjoint analysis
6
d)Principal Components Analysis (PCA) and Factor Model:
10
Procedure Principal Component Analysis (PCA), Maximum
Likelihood Estimation Method, Factor Rotations, Varimax
Rotation,
Estimation of Factor Scores.
e) Cluster Analysis: Measures of Association for Continuous

Variables, Measures of Association for Binary Variables,
Agglomerative Hierarchical Clustering, Ward’s Method, K- 10
Means Procedure, K-Nearest Neighbors
___________ ____________
Signature Signature

SVKM’s NMIMS
Time Series Analysis:

Characteristics of Time Series Data, Stationarity,Unit root;
4 Detrending and De-seasonalizing , Autoregressive Moving
10
Average (ARIMA) model; Exponential Smoothing Techniques;
Forecasting through ARIMA and ARMA with Exponential
smoothing; ACF and PACF, Univariate Time Series Models
Total 60
Text Books:
1. An Introduction to Statistical learning with application in R . Hastie T, Robert T.
(2014). Springer Science Business Media: New York
2. Hair, Black, Babin, Anderson and Tatham (2009). Multivariate Data Analysis,
Pearson
Reference Books:
1. Statistics for Management, Seventh Edition, by Richard I. Levin, David S. Rubin,
Pearson
2. An Introduction to Categorical Data Analysis. Agresti, A. (2012). John Wiley &
sons
3. The Element of Statistical Learning, Data mining, Inference and Prediction. Hastie,
T, Tibshirani, R, & Friedman, J. (2011). New York: Springer Series in Statistics.
4. Gujarati, Damodar N, and Dawn C. Porter. Basic Econometrics. Boston, Mass:
McGraw-Hill, 2009

Test Marks: 20
Term Work Marks: 30

1. Two class tests.

Course/Module: Deep Learning Module Code: MTAI02004
___________ ____________
Signature Signature

SVKM’s NMIMS
Tutorial Internal Continuous

Lecture Practical Term End
(Hours Assessment
(Hours per (Hours Credit Examinations (TEE)
per (ICA)
week) per week) (Marks -100
week) (Marks -50)
in Question Paper)
Pre-requisite: Machine Learning and Data Mining
Objectives: Expand the knowledge gained in Database Management Systems in
several directions like Non-Relational data models, deductive (Intelligent) database
systems, Distributed systems, web based systems and object oriented systems etc.
Course Outcomes:
1. Design database using concept of extended entity relationship model.
2. Implement functions and procedures using concepts of PL/SQL
3. Implement object oriented concepts in database.
4. Compare and contrast different types of advance database management systems.
5. Describe database Administration and its management.
Detailed Syllabus:
1. Introduction to deep learning: Neural network basics: 07
Supervised Learning with Neural Networks, Computation
graph, Broadcasting in Python
2. Shallow neural networks: Computing a Neural Network's 07
Output, Vectorizing across multiple examples,
Explanation for Vectorized Implementation, Activation
functions, Derivatives of activation functions, Gradient
descent for Neural Networks, Back-propagation intuition,
Random Initialization
3. Deep Neural Networks: Deep L-layer neural network, 07
Forward Propagation in a Deep Network, Getting your
matrix dimensions right, Building blocks of deep neural
networks, Forward and Backward Propagation,
Parameters verses Hyper parameters
4. Improving Deep Neural Networks: Hyper parameter 05
tuning, Regularization and Optimization: Practical
aspects of Deep Learning: Initialization, Regularization,
Gradient Checking
___________ ____________
Signature Signature

SVKM’s NMIMS
5. Optimization algorithms: Mini-batch gradient descent, 06

Understanding mini-batch gradient descent, exponentially
weighted averages, Understanding exponentially
weighted averages, bias correction in exponentially
weighted averages, Gradient descent with momentum
6. Hyperparameter tuning, Batch Normalization and 06
Programming Frameworks
7. Convolutional Neural Networks: Foundations of 06
Convolutional Neural,
Deep convolutional models: case studies, Object detection,
Special applications: Face recognition & Neural style
transfer
8. Sequence Models: Recurrent Neural Networks 04
Data Flow programming: TensorFlow 12
Total 60
Text Books:
1. Deep Learning by Ian Goodfellow, Yoshua Bengio, Aaron Courville
2. Deep Learning Hardcover – 3 Jan 2017 by Ian Goodfellow, Yoshua Bengio, Aaron
Courville, Francis Bach
Reference Books:
1. Deep Learning - 3 Jan 2017 by Ian Goodfellow, Yoshua Bengio, Aaron Courville,
Francis Bach
2. Deep Learning, Vol. 2: From Basics to Practice by Andrew Glassner

Test Marks: 20
Term Work Marks: 30

2. Two class tests.
___________ ____________
Signature Signature

SVKM’s NMIMS
Program: M. Tech. Artificial Intelligence Semester : II

Course/Module : Speech Recognition Module Code : MTAI02005
Lecture Practical Tutorial Internal
Continuous
(Hours (Hours (Hours
Credit Assessment Term End Examinations (TEE)
per per per (Marks -100 in Question Paper)
(ICA)
week) week) week) (Marks -50)
Scaled to 50
4 0 0 4 Scaled to 50 marks
Marks
Pre-requisite: CS/CP
Objectives:
In the course student will build working speech recognition systems, build their own
synthetic voice and build a complete telephone spoken dialog system. This work will be
based on existing toolkits. Details of algorithms, techniques and limitations of state of the
art speech systems will also be presented. This course is designed for students wishing
understand how to process real data for real applications, applying statistical and
machine learning techniques as well as working with limitations in the technology
Outcomes:
Speech Processing offers a practical and theoretical understanding of how human speech
can be processed by computers. It covers speech recognition, speech synthesis and
spoken dialog systems.
Detailed Syllabus:
1 Human Speech, Computer Speech 04
ASR: Signal Processing, ASR: Template matching, ASR: HMMs 04
slides Reading 1, ASR: Acoustic Modeling, ASR: Language 04
2
Modeling, ASR: Systems 04
ASR: Language Modeling 2 04
TTS: Text Analysis, TTS: Pronunciation, TTS: Prosody, TTS: 04
3 Waveform I, TTS: Waveform II, TTS: Voice building, TTS:
Evaluation, TTS: Signal Processing, TTS: Talking Heads and Singing 04
___________ ____________
Signature Signature

SVKM’s NMIMS
Multilingual Speech Processing, SPICE

Speech to Speech Translation I, Speech to Speech Translation II,
Spoken Dialog Systems: Intro, Spoken Dialog Systems:
Components, Spoken Dialog Systems: VoiceXML, Spoken Dialog
4 16
Systems: beyond simple dialogs; Olympus intro, Spoken Dialog
Systems: Olympus II, Spoken Dialog Systems: deployment, Spoken
Dialog Systems: Personal Digital Assistants, Spoken Dialog Systems:
Evaluation
Voice Conversion I, Speaker ID
5 Voice Conversion/Deidentification, Computer Aided Language 16
Learning, Present and Future Speech Problems
Total 60
Text Books:
1. Spoken Language Processing by Xuedong Huang, Alex Acero and Hsiao-wuen
Hon, Prentice Hall (ISBN 0-13-22616-5).
2. Automatic Speech Recognition: A Deep Learning Approach (Signals and
Communication Technology) 2015th Edition
Reference Books:
1. Robust Automatic Speech Recognition: A Bridge to Practical Applications 1st
Edition by Jinyu Li (Author), Li Deng (Author), Reinhold Haeb-Umbach (Author),
Yifan Gong (Author)
2. Speech And Language Processing 2ed_draft2007 by Jurafsky Martin

Test Marks: 20
Term Work Marks: 30

2. Two class tests.
Program: M. Tech. – Artificial Intelligence Semester: II
___________ ____________
Signature Signature

SVKM’s NMIMS
Course/Module : Research Project – II Module Code: MTAI02008

Lecture Practical Tutorial Internal Continuous Term End
(Hours (Hours (Hours Assessment Examinations (TEE)
Credit
per per per (ICA) (Marks -- in
week) week) week) (Marks -50) Question Paper)
0 4 0 2 Scaled to 50 marks -
Pre-requisite: Nil
Objectives:
 Apply all learning in this semester and work on a topic of research leading to a
paper in journal or seminar.
Outcomes:
After completion of the course, students would be able to:
 Learn research methodology
 Write a technical paper
Detailed Syllabus: ( per session plan )
1 Select a topic of research 04
2 Paper review 15
3 Make a strategy to work on a project (subject finalization) 15
4 Actual research 20
5. Finalization of paper for publication 06
Total 60
Text Books:
1. Research methodology
2. Actual paper reading

Test Marks --
Term Work Marks 50
Total Marks : 50
Details of Term work: As per institute norms
___________ ____________
Signature Signature

SVKM’s NMIMS
Program: M. Tech. – Artificial Intelligence Semester : III

Course/Module: Capstone project Module Code : MTAI03001
Internal Continuous
Lecture Practical Tutorial Term End
Assessment
(Hours per (Hours per (Hours per Credit Examinations (TEE)
(ICA)
week) week) week) (Marks --)
(Marks -50)
4 4 0 6 Marks Scaled to 50 ---
Pre-requisite: All subject of M. Tech AI
Objectives:
 Student to understand topics in Artificial Intelligence and Data Science and its application to solve
any one or more industry problems
Outcomes:
 It is expected to come up with a paper in reputed journal with guidance from any faculty members
1 Contemporary research papers review 5
2 Identification of problem statement 5

3 Data collection and validation 5
4 Tool identification and usage 5
5 Technique to solve the problem including Model building 5
6 Model validation 5
7 Research 10
8 Publication 5
9 Next steps 5
10 Final Project presentation in front of industry/expert panel 10
Total 60
Text Books:
1. Contemporary research paper review
Reference Books:
1. NA
___________ ____________
Signature Signature
M. TECH /AI/2020-21/SEM III /Page 1 of 14

SVKM’s NMIMS

Test Marks 20
Term Work Marks 30
Total Marks : 50

2. Two class tests.
___________ ____________
Signature Signature

SVKM’s NMIMS
Program: M. Tech. – Artificial Intelligence Semester :III

Course/Module: Big Data Technology Module Code : MTAI03002
Internal Continuous Term End Examinations
Assessment (TEE)
(Hours per (Hours per (Hours per Credit
(ICA) (Marks -100 in Question
week) week) week)
(Marks -50) Paper)
3 0 0 3 Marks Scaled to 50 Marks Scaled to 50
Pre-requisite: Python/Programming language/SQL
Objectives:
Big data Analytics refers to skills, practices and techniques used in converting large scale data and its
storage about computation challenges to convert data into information and knowledge that aid making
business decision. This discipline consists of an understanding of:
 Distributed storage and computation and usage of concept like Map Reduce, developed and widely
used by Google search engine
 The use of the above analysis and visualization to aid decision making
Outcomes:
 Upon completion of this course one will be able to setup, manage and exploit big data cluster for
analytics from social media. This will make student ready to setup and manage environment of
cluster, cloud, grid and stream computing.
 One will be able to setup Hadoop or Casandra cluster for handling big data and distributed file
system and computing. Helps work on large scale systems and social media systems.
 One will be able to provide cyber security as an expert to high net asset systems with critical data
1 Introduction to Big Data 02
Big Data
 MapReduce
01
 Hadoop eco system
 Word Count MapReduce 02
2  Different tools on Big data Platform
 Vector data (newspaper article or document search) 02
 PageRank Algorithm
02
 Twitter Data Analytic - Social Media mining
 Images
 Data Visualization 02
3  Implementation of a search engine
 Stream data analytics 02
___________ ____________
Signature Signature

SVKM’s NMIMS
Hive, storage of Hive data (database) in HDFS, Query writing to

4 achieve business tasks, Database management, Query optimization, 8
Views and Partition
5 Pig – Data flow programming, Storing data in HDFS / Hood 8
6 MongoDB, Database creation, Query building, regular expression 8
7 A mini project related to AI 8
Total 45
Text Books:
1. Big Data, Black Book: Covers Hadoop 2, MapReduce, Hive, YARN, Pig, R and Data Visualization,
By DT Editorial Services, 2016
2. Programming Hive. By Jason Rutberglen, Dean Wampler, Edward Copriolo, 2012
3. Programming Pig by Anal Gates, 2011 (look for newer edition of book)
4. MongoDB: The Definitive Guide, by Kristina Chodorow, 2013
Reference Books:
1. Hadoop, The Definitive Guide, by Tom White, 2015
2. Mining of Massive Datasets, by Jure Leskovec, Anand Rajaraman, Jeffrey D. Ullman, 2015

Test Marks 20
Term Work Marks 30
Total Marks : 50

2. Two class tests.
___________ ____________
Signature Signature

SVKM’s NMIMS

Course/Module: Advanced Computer Vision Module Code : MTAI03003
Internal Continuous
Tutorial Term End
Lecture Practical Assessment
(Hours Examinations (TEE)
(Hours per (Hours Credit (ICA)
per (Marks -100 in
week) per week) (Marks -50)
week) Question Paper)
Pre-requisite: Computer Vision
Objectives:
 Understand advancement and contemporary Computer Vision research
Outcomes:
 Students will be able to understand contemporary research work on computer vision field in
the world
 Hand on case studies on newer algorithms on computer vision
Sketch2Photo: Internet Image Montage. ACM SIGGRAPH ASIA 2009,
1 3
ACM Transactions on Graphics.
Unsupervised Representation Learning with Deep Convolutional
2 3
Generative Adversarial Networks.
3 Image Style Transfer Using Convolutional Neural Networks. 3
4 Network Dissection: Quantifying Interpretability of Deep Visual
4
Representations
5 Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images 4
6 Deep Learning on Point Sets for 3D Classification and Segmentation 4
7 Frustum PointNets for 3D Object Detection from RGB-D Data 4
8 Explaining and Harnessing Adversarial Examples. 4
9 Adversarial Patch. 4
10 Learning Features by Watching Objects Move. 4
11 Matching Networks for One Shot Learning. 4
12 Final Project Poster Session 4
Total 45
Text Books:
1. Contemporary research papers from 2016 to 2018
___________ ____________
Signature Signature

SVKM’s NMIMS
2. Computer Vision: Algorithms and Applications Richard Szeliski, 2011

Reference Books:
1. Computer vision guide

Test Marks 20
Term Work Marks 30
Total Marks : 50

2. Two class tests.
___________ ____________
Signature Signature

SVKM’s NMIMS

Course/Module: Advanced Data Mining for AI Module Code : MTAI03004
Practical Tutorial Internal Continuous
Lecture Term End Examinations
(Hours (Hours Assessment
(Hours per Credit (TEE) (Marks -100 in
per per (ICA)
week) week) (Marks -50)
Pre-requisite: Data mining
1. An introduction to database systems, covering SQL and related programming systems.
2. A sophomore-level course in data structures, algorithms, and discrete math.
3. A sophomore-level course in software systems, software engineering, and programming
languages.
Objectives:
Advancement in research and knowledge discovery process, key data mining techniques, efficient
high performance mining algorithms, exposure to applications of data mining (bioinformatics and
intrusion detection). The course titled “Web Mining,” was designed as an advanced graduate course,
although it has become accessible and interesting to advanced postgraduates.
Outcomes:
 Distributed file systems and map-reduce as a tool for creating parallel algorithms that succeed
on very large amounts of data.
 Similarity search, including the key techniques of min-hashing and locality sensitive hashing.
 Data-stream processing and specialized algorithms for dealing with data that arrives so fast it
must be processed immediately or lost.
 The technology of search engines, including Google’s PageRank, link-spam detection, and the
hubs-and-authorities approach.

1 Distributed file systems and map-reduce as a tool for creating parallel
03
algorithms that succeed on very large amounts of data.
2 Similarity search, including the key techniques of minhashing and
03
locality sensitive hashing.
Data-stream processing and specialized algorithms for dealing with
3 06
data that arrives so fast it must be processed immediately or lost.
The technology of search engines, including Google’s PageRank, link-
4 06
spam detection, and the hubs-and-authorities approach.
___________ ____________
Signature Signature

SVKM’s NMIMS
5 Frequent-item-set mining, including association rules, market-baskets,

03
the A-Priori Algorithm and its improvements.
6 Algorithms for clustering very large, high-dimensional datasets. 06
Two key problems for Web applications: managing advertising and
7 06
recommendation systems.
8 Algorithms for analyzing and mining the structure of very large
06
graphs, especially social-network graphs.
Techniques for obtaining the important properties of a large dataset by
9 dimensionality reduction, including singular-value decomposition and 06
latent semantic indexing.
Total 45
Text Books:
1. Introduction to Data Mining, Tan, Steinbach and Kumar, Addison Wesley, 2006
2. Data Mining: Concepts and Techniques, J. Han & M. Kamber, Morgan Kaufmann, 2006.
Reference Books:
1. Data Mining Analysis and Concepts, M. Zaki and W. Meira (the authors have kindly made an
online version available): http://www.dataminingbook.info/uploads/book.pdf
2. Mining of Massive Datasets, J. Leskovec, A. Rajaraman and J. Ullman
http://infolab.stanford.edu/~ullman/mmds/book.pdf
3. Data Mining, Charu Aggarwal, Springer, 2015. Should be available online off SpringerLink.

Test Marks 20
Term Work Marks 30
Total Marks : 50

2. Two class tests.
___________ ____________
Signature Signature

SVKM’s NMIMS

Course/Module: Financial Analytics using time series and LSTM Module Code : MTAI03005
Practical Tutorial Internal Continuous
Lecture Term End Examinations
(Hours (Hours Assessment
(Hours per Credit (TEE) (Marks -100 in
per per (ICA)
week) week) (Marks -50)
Pre-requisite: Probability/Python/Deep learning/Neural Network
Objectives:
Aim to understand sequential data, relationship between previous data and current data by building
a Long Short-term memory model of Neural Network
Outcomes:
1. Understand Neural network
2. Advance research in LSTM
1 Understanding Neural network 2
2 Understanding Time Series 10
3 Different models in time series (ARIMA, ARMA etc.) 2
4 AI Neural Network in financial Data 2
5 Recurrence Neural Network and its advantage and disadvantage 2
6 Long Short-term Memory Model 5
7 Model Building 3
8 Model Validation 3
9 Working with Time series data (Sensex) 3
10 Model Validation 3
11 Model Deployment 5
12 Conclusion with a project 5

Total 45
___________ ____________
Signature Signature

SVKM’s NMIMS
Text Books:
1. RECURRENT NEURAL NETWORKS, Design and Applications, by L.R. Medsker, L.C. Jain,
2016
2. Few more latest text books
Reference Books:
1. http://www.statslab.cam.ac.uk/~rrw1/opt/O.pdf

Test Marks 20
Term Work Marks 30
Total Marks : 50

2. Two class tests.
___________ ____________
Signature Signature

SVKM’s NMIMS

Course: Probabilistic Robotics Module Code : MTAI03006
Lecture Internal Continuous Term End Examinations
Practical Tutorial
(Hours Assessment (TEE)
(Hours per (Hours Credit
per (ICA) (Marks -100 in
week) per week)
week) (Marks -50) Question Paper)
Pre-requisite: Probability/Python/Programming language/Robotics
Objectives:
Robotics is the science of perceiving and manipulating the physical world through computer-
controlled mechanical devices. Examples of successful robotic systems include mobile platforms for
planetary exploration, robotics arms in assembly lines, cars that travel autonomously on highways,
actuated arms that assist surgeons.
Robotics systems have in common that they are situated in the physical world, perceive their
environments through sensors, and manipulate their environment through things that move.
Outcomes:
1. Environments. Physical worlds are inherently unpredictable. While the degree of uncertainty in
well-structured environments such assembly lines is small, environments such as highways and
private homes are highly dynamic and unpredictable.
2. Sensors. Sensors are inherently limited in what they can perceive. Limitations arise from two
primary factors. First, range and resolution of a sensor is subject to physical laws. For example,
Cameras can’t see through walls, and even within the perceptual range the spatial resolution of
camera images is limited. Second, sensors are subject to noise, which perturbs sensor
measurements in unpredictable ways and hence limits the information that can be extracted from
sensor measurements.
3. Robots. Robot actuation involves motors that are, at least to some extent, unpredictable, due effects
like control noise and wear-and-tear. Some actuators, such as heavy-duty industrial robot arms,
are quite accurate. Others, like low-cost mobile robots, can be extremely inaccurate.
4. Models. Models are inherently inaccurate. Models are abstractions of the real world. As such, they
only partially model the underlying physical processes of the robot and its environment. Model
errors are a source of uncertainty that has largely been ignored in robotics, despite the fact that
most robotic models used in state-or-the-art robotics systems are rather crude.
5. Computation. Robots are real-time systems, which limits the amount of computation that can be
carried out. Many state-of-the-art algorithms (such as most of the algorithms described in this
book) are approximate, achieving timely response through sacrificing accuracy.
1 INTRODUCTION 3
___________ ____________
Signature Signature

SVKM’s NMIMS
2 RECURSIVE STATE ESTIMATION 3

3 GAUSSIAN FILTERS 3
4 NONPARAMETRIC FILTERS 3
5 ROBOT MOTION 3
6 MEASUREMENTS 3
7 MOBILE ROBOT LOCALIZATION 3
8 GRID AND MONTE CARLO LOCALIZATION 3
9 OCCUPANCY GRID MAPPING 3
10 SIMULTANEOUS LOCALIZATION AND MAPPING 3
11 THE EXTENDED INFORMATION FORM ALGORITHM 3
12 THE SPARSE EXTENDED INFORMATION FILTER 3
13 MAPPING WITH UNKNOWN DATA ASSOCIATION 3
14 FAST INCREMENTAL MAPPING ALGORITHMS 3
15 MARKOV DEVISION PROCESSES 3
Total 45
Text Books:
1. Probabilistic Robotics, by Sebastian Thrun, Wolfram Burgard, Dieter Fox, 2012
Reference Books:
1. Robotics Hand book

Test Marks 20
Term Work Marks 30
Total Marks : 50

2. Two class tests.
3. Minimum two assignment
___________ ____________
Signature Signature

SVKM’s NMIMS

Course/Module: Optimization Module Code: MTAI03007
Internal Continuous Term End Examinations
Assessment (TEE)
(Hours (Hours (Hours Credit
(ICA) (Marks -100 in
per week) per week) per week)
(Marks -50) Question Paper)
Pre-requisite: Basis Mathematics/Python
Objectives:
Aim to understand different optimization techniques and its application
Outcomes:
1. Lagrangian methods
2. Linear programming in the nondegenerate case
3. Network problems
4. Practice and applications
1 Preliminaries 3
2 Lagrangian Methods 3
3 The Lagrangian Dual 3
4 Solutions to Linear Programming Problems 3
5 The Simplex Method 3
6 The Simplex Tableau 3
7 Algebra of Linear Programming 4
8 Shadow Prices and Lagrangian Necessity 4
9 Two Person Zero-Sum Games 4
10 Maximal Flow in a Network 5
11 Minimum Cost Circulation Problems 5
12 Transportation and Transshipment Problems () 5
___________ ____________
Signature Signature

SVKM’s NMIMS
Total 45
Text Books:
1. Linear Programming and Network Flows, by Bazaraa, M., Jarvis, J. and Sherali, H, fourth
edition, 2014, Wiley.
2. Introduction to Linear and Non-Linear Programming, Luenberger, D. second edition, 2014,
Addison-Wesley.
3. Linear programming: foundations and extensions. Vanderbei, R. J. Kluwer 2015 (61.50
hardback).
4. Optimization, by Richard Weber, 2010
Reference Books:
1. http://www.statslab.cam.ac.uk/~rrw1/opt/O.pdf

Test Marks 20
Term Work Marks 30
Total Marks : 50

2. Two class tests.
___________ ____________
Signature Signature

Syllabus MTech AI

Uploaded by

Copyright:

Available Formats

Syllabus MTech AI

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Syllabus MTech AI

Uploaded by

Copyright:

Available Formats

SVKM’s NMIMS

Mukesh Patel School of Technology Management & Engineering

Program: M. Tech Artificial Intelligence Semester: I

4 0 0 4 Scaled to 50 Marks Scaled to 50 marks

M. TECH /AI/2020-21/SEM I /Page 1 of 10

5. Markov decision processes, reinforcement learning. 12

6. AI applications to natural language processing (NLP) 04

Total Marks of Internal Continuous Assessment (ICA): 50 Marks

Distribution of ICA Marks:

Description of ICA Marks

Details of Term work:

M. TECH /AI/2020-21/SEM I /Page 2 of 10

Program: M. Tech Artificial Intelligence Semester : I

M. TECH /AI/2020-21/SEM I /Page 3 of 10

Any other information: NIL

Total Marks of Internal Continuous Assessment (ICA): 50 Marks

M. TECH /AI/2020-21/SEM I /Page 4 of 10

Distribution of ICA Marks:

Description of ICA Marks

Details of Term work:

M. TECH /AI/2020-21/SEM I /Page 5 of 10

Program: M. Tech Artificial Intelligence Semester: I

M. TECH /AI/2020-21/SEM I /Page 6 of 10

Pattern Analysis : Clustering: K-Means, K-Medoids, Mixture of

Total Marks of Internal Continuous Assessment (ICA): 50 Marks

Distribution of ICA Marks:

Description of ICA Marks

Details of Term work:

M. TECH /AI/2020-21/SEM I /Page 7 of 10

Program: M. Tech Artificial Intelligence Semester : I

M. TECH /AI/2020-21/SEM I /Page 8 of 10

Total Marks of Internal Continuous Assessment (ICA): 50 Marks

Distribution of ICA Marks:

Description of ICA Marks

Details of Term work:

M. TECH /AI/2020-21/SEM I /Page 9 of 10

Program: M. Tech. – Artificial Intelligence Semester: I

Total Marks of Internal Continuous Assessment (ICA): 50 Marks

Details of Term work: As per institute norms

M. TECH /AI/2020-21/SEM I /Page 10 of 10

Program: M. Tech Artificial Intelligence Semester: II

M. TECH /AI/2020-21/SEM II /Page 1 of 13

Speech Tagging, POS Taggers, Practice Training a POS Tagger,

M. TECH /AI/2020-21/SEM II /Page 2 of 13

11. Precision, Recall, F-score, Map, Semantic Relations; UNL; 05

Details of Internal Continuous Assessment (ICA):

Details of Term work:

M. TECH /AI/2020-21/SEM II /Page 3 of 13

Program: M. Tech Artificial Intelligence Semester: II

M. TECH /AI/2020-21/SEM II /Page 4 of 13

transformation using matrices, the orientation matrix &

M. TECH /AI/2020-21/SEM II /Page 5 of 13

2. Ronald Siegwart & Illah R Nourbaksh, Introduction to autonomous mobile Robots,

Details of Internal Continuous Assessment (ICA):

Details of Term work:

Program: M. Tech. Artificial Intelligence Semester : II

M. TECH /AI/2020-21/SEM II /Page 6 of 13

Course/Module: Advanced Statistical Learning Module Code : MTAI02003

e) Cluster Analysis: Measures of Association for Continuous