Graduate Program in Artificial Intelligenceby

Rawalpindi Medical University (RMU),

Rawalpindi

Background:
The Rawalpindi Medical University (RMU) has taken the initiative and lead by
starting a program in Artificial Intelligence at the graduate level to help establish
and grow the industry in medicine field in Pakistan.

Program Educational Objectives:

PEO1: Have a strong competence in Artificial Intelligence resulting in
successful careers.
PEO2: Pursuing research and innovation and be able to provide modern
solutions to technical problems.
PEO3: To apply as well as create Artificial Intelligence based knowledge at par
with the developments at both national and international level.

Curriculum:
The proposed curriculum is unified for all RMU partner universities. For the sake
of uniformity and ease of transfer of courses, a national course code has also been
defined for each course. This will be treated as a reference for course
compatibility between RMU partner institutions.

Core Courses

National
Course Course Name CHs
Code

AI 801 Artificial Intelligence (3)

AI 802 Machine Learning (3)

 AI 803 Mathematics for (3)
Artificial Intelligence

Elective Courses

National
Course Course CHs
Code

AI 811 Deep Learning (3)

AI 812 Probabilistic Graphical (3)

Models

AI 813 Multi-agent Systems (3)

AI 814 Knowledge Representation (3)

and Reasoning

AI 815 Neural Networks (3)

AI 818 Probabilistic Robotics (3)

AI 819 Text Analytics (3)

AI 821 Computer Vision (3)

AI 822 Advanced Image Processing (3)

AI 823 Speech Processing (3)

AI 824 Data Acquisition and (3)

Control

AI 825 Sensors and Sensing (3)

AI 826 Human Robot Interaction (3)

AI 827 Simultaneous Localization (3)

and Mapping
AI 828 Complex Adaptive Systems (3)

AI 829 Social Simulations (3)

AI 831 Intelligent Systems (3)

AI 832 Reinforcement Learning (3)

AI 834 Robotic Grapping and (3)

Fixture

AI 835 Rehabilitation and Assistive (3)

Robotics

AI 836 Bio Robotics (3)

AI 837 Intelligent Transportation (3)

Systems
AI 838 Serious Games (3)

AI 841 Data Mining (3)

AI 842 Information Retrieval (3)

AI 843 Natural Language (3)

Processing

AI 844 Semantic Web (3)

AI 845 Internet of Things (3)

AI 846 Computational Creativity (3)

AI 851 Advanced Signal Processing (3)

AI 852 Modelling and Simulation (3)

AI 853 Advanced Programming in (3)

Python
AI 854 Data Analysis and (3)
Visualization

AI 855 Cyber Security (3)

AI 856 Ethical Machines (3)

Detailed Curriculum (Courses)

1. AI 832: Reinforcement Learning

Textbook
• Reinforcement Learning: An Introduction by Sutton and Barto. Also
available at http://incompleteideas.net/book/the-book-2nd.html
• Handouts and research articles may also be used by the instructor.

Objective
To realize the dreams and impact of AI requires autonomous systems that learn
to make good decisions. Reinforcement learning is one powerful paradigm for
doing so, and it is relevant to an enormous range of tasks, including robotics, game
playing, consumer modeling and healthcare. This class will provide a solid
introduction to the field of reinforcement learning and students will learn about
the core challenges and approaches, including generalization and exploration.
Through a combination of lectures, and written and coding assignments, students
will become well versed in key ideas and techniques for RL. Assignments will
include the basics of reinforcement learning as well as deep reinforcement
learning — an extremely promising new area that combines deep learning
techniques with reinforcement learning. In addition, students will advance their
understanding and the field of RL through a final project.

Pre-Requisite
Linear Algebra, Probability, Machine Learning and Deep Learning

Course Outcome
During the course, students will learn to:

• Define the key features of reinforcement learning that distinguishes it

from AI and non-interactive machine learning.
• Given an application problem (e.g. from computer vision, robotics, etc),
decide if it should be formulated as a RL problem; if yes be able to define
it formally (in terms of the state space, action space, dynamics and reward
model), state what algorithm (from class) is best suited for addressing it
and justification.
• Implement in code common RL algorithms.
• Describe (list and define) multiple criteria for analyzing RL algorithms and
evaluate algorithms on these metrics: e.g. regret, sample complexity,
computational complexity, empirical performance, convergence, etc.
• Describe the exploration vs exploitation challenge and compare and
contrast at least two approaches for addressing this challenge (in terms of
 performance, scalability, complexity of implementation, and theoretical
guarantees)

Course Outline

Allocated
Topics
Periods
• Introduction to Reinforcement Learning 45
• Markov Processes
• Policy Search and Iteration
• Value Iteration
• Policy Evaluation
• Model Free Learning: Q-Learning and SARSA
• RL with function approximation
• Imitation Learning in Large spaces
• Exploration/Exploitation
• Batch Reinforcement Learning

2. AI 812: Probabilistic Graphical Models

Textbook
• Probabilistic Graphical Models: Principles and Techniques by Daphne
Koller and Nir Friedman. MIT Press.
• Handouts and research articles may also be used by the instructor.

Objective
Probabilistic graphical models are a powerful framework for representing
complex domains using probability distributions, with numerous applications in
machine learning, computer vision, natural language processing and
computational biology. Graphical models bring together graph theory and
probability theory, and provide a flexible framework for modeling large
collections of random variables with complex interactions. This course will
provide a comprehensive survey of the topic, introducing the key formalisms and
main techniques used to construct them, make predictions, and support decision-
making under uncertainty.

Pre-Requisite
Basic probability theory, statistics, programming, algorithm design and analysis.

Course Outcome
During the course, students will learn to develop the knowledge and skills
necessary to design, implement and apply these models to solve real problems.
Be able to describe directed and undirected graphical models, exact and
approximate inference methods and estimation of parameters.

Course Outline
Allocated
Topics
Periods
• Introduction, Probability Theory, Bayesian Networks 45
• Undirected models
• Learning Bayes Nets
• Exact Inference; Message Passing
• Sampling
• MAP Inference; Structured prediction
• Parameter Learning
• Bayesian Learning; Structure Learning
• Exponential families; variational inference

3. CSE 860: Artificial Intelligence (3-0)

Textbook: [AIMA] Artificial Intelligence: A Modern Approach (2nd
Edition), by Stuart Russel and Peter Norvig, Prentice Hall, 2002
ISBN-10: 0137903952, ISBN-13: 978-0137903955
Reference Books:
• Artificial Intelligence Structures and Strategies for Complex Problem
Solving by George F Lugar, Addison Wesley, 4th Ed 2002
• Artificial Intelligence: A New Synthesis by Nils Nilsson, Morgan
Kaufman, 1997.
Objective:
The primary objective of this course is to introduce the basic principles and
applications of Artificial Intelligence. Programming assignments are used to
help clarify basic concepts. The emphasis of the course is on teaching the
fundamentals, and not on providing a mastery of specific commercially
available software tools or programming environments. In short, this is
course is about the design and implementation of intelligent agents---
software or hardware entities that perform useful tasks with some degree of
autonomy.
Course Outcome:
Upon successful completion of the course, students will understand the basic
areas of artificial intelligence including problem-solving, knowledge
representation, reasoning, decision making, planning, perception and action,
and learning. Students will also be able to
 design and implement key components of intelligent agents of moderate
complexity in C and/or Lisp or Prolog and evaluate their performance.
Graduate students are expected to develop familiarity with current research
problems, research methods, and the research literature in AI.
Course Outline:
Artificial Intelligence (AI) seeks to understand the mechanisms underlying
thought and intelligent behavior, and their embodiment in machines. This
course approaches AI by using Intelligent Agents as an integrating
perspective on the key topics in intelligent behavior.

Topics Allocated
Periods
Introduction to AI 45
Definitions (Acting Humanly, Cognitive, “laws of
Thought”, Rational agent
approaches
Historical perspective
Physical symbol system hypothesis

Intelligent agents
Agents and Environment
The concept of rationality
Performance measures
Omniscience, learning and autonomy
Nature of environments, Task environments and their
Properties

The Structure of agents

Simple Reflex agent
Model based agent
Goal Based agents
Utility based agents
Learning agents

Problem solving by searches

Problem solving agents
Problem formulating
Measuring performance

Search Strategies
Uninformed Searches
Breadth first
Depth first
Depth limited
Iterative deepening depth-first
Bidirectional
Comparison of Uninformed problem-solving methods

Informed searches
Greedy best-first
A*
Heuristic Functions (learning, devising)
Local search algorithms
Hill climbing
Simulating annealing
Local beam
Genetic algorithms

Constraints Satisfaction problems

Basics of CSP
Structure of problems
Backtracking, forward chaining
Variable and value ordering
Intelligent backtracking
Local searches for CSPs
Adversarial Searches
Games
Optimal decisions
Mini-max algorithm
Alpha-Beta pruning

Logical agents
Knowledge-based agents
Propositional logic (syntax, semantics)
Conjunctive/disjunctive Normal form, Horn clauses
Reasoning in Propositional logic
Resolution
Forward and backward chaining
Reasoning algorithms
First-Order Logic (syntax, semantics)
Inference in FOL
Conjunctive Normal form
Unification and lifting, forward and backward
chaining, resolution
Comparison of two representational languages
 Machine Learning
Introduction, induction, Types of machine learning
Nearest Neighbors
Decision Trees
Neural Networks
Learning Conjunctions
Linear and non-Linear
separabilityEvaluating learning
algorithms

Natural language Understanding

Levels of language analysis
Types of grammar Parsing
(Top-down, bottom-up)natural
language applications.

4. EC 803: Computer Vision (3-0)

Textbook: Computer Vision: A Modern Approach, D. Forsyth and J.
Ponce, Prentice-Hall, 2001 (FP). ISBN-10: 0130851981, ISBN-13: 978-
0130851987
Reference Book:
• Computer Vision: Algorithms and Applications, Richard Szeliski,
2009 (RS). ISBN-10: 1848829345, ISBN-13: 978-1848829343
• Computer Vision, Linda G. Shapiro and George Stockman, Prentice
Hall, (2001).
• Computer Vision and Image Processing, Tim Morris, Palgrave
Macmillan, (2004).
Objective:
The objective of this course is to understand the basic issues in computer
vision and major approaches that address them. Even though Computer
Vision is being used for many practical applications today, it is still not a
"solved" problem. Hence, definitive solutions are available only rarely; most
of the time, we will discuss alternatives and their limitations.
Course Outcome:
After completing the course, the students may expect to have the knowledge
needed to read and understand the more advanced topics and current research
literature, and the ability to start working in industry or in academic research.
Course Outline:
 The primary topics to be covered are chapters 13 through 21 in the textbook.
Mostly, the material covered in the text book will be followedbut, in some
cases, the material will be supplemented by newer methods, which are
available only in the form of research papers or tutorial articles.
Following is a list of topics expected to be covered, in anticipated order,
and with expected time to be spent on them. This list is intended to be only
indicative, the actual topics, the order and the time may vary somewhat
depending on various factors including student interests and preparation.

Topics Allocated
Periods
Image Formation 45
- Sampling
- Quantization
- Geometry
- Photometry
- Color
Calibration
Filtering and Convolution
Feature Extraction
- Corners, edges, regions
Segmentation and grouping
- Parametric fitting,
- Hough transform,
- Tensor Voting
Stereo
Structure and motion
Dense motion and Optical flow
Range Image Analysis
Recognition

5. RIME 833: Deep Learning

Textbook
1. Deep Learning. By Ian Goodfellow, Yoshua Bengio, and Aaron Courville,
MIT Press, 2016. Also available at www.deeplearningbook.org
Handouts and research articles may also be used by the instructor.

Objective
2. Computer Vision has become ubiquitous in our society, with applications
in search, image understanding, apps, mapping, medicine, drones, and self-
driving cars. Core to many of these applications are visual recognition tasks
such as image classification, localization and detection. Recent developments in
neural network (aka “deep learning”) approaches have greatly advanced the
performance of these state-of-the-art visual recognition systems. This course is
a deep dive into details of the deep learning architectures with a focus on learning
end-to-end models for these tasks, particularly image classification.

Pre-Requisite
3. Linear Algebra, Probability, Machine Learning
Course Outcome
4. During the course, students will learn to implement, train and debug their
own neural networks and gain a detailed understanding of cutting-edge research
in computer vision and its application for robotics. The final assignment will
involve training a multi-million parameter convolutional neural network and
applying it on a large dataset.

Course Outline
4. The course covers the techniques and technology to set up the problem of image
recognition, the learning algorithms (e.g. backpropagation), practical engineering
tricks for training and fine-tuning the networks.
Allocated
Topics
Periods
• Machine Learning Basics 45
• Deep Feedforward Networks
• Regularization for Deep Learning
• Optimization for Training Deep Models
• Convolutional Neural Networks
• Sequence Modeling: Recurrent Neural Networks
• Applications of Deep Learning

6. RIME 813: Robotic Grasping and Fixturing

Textbook
1. Fundamentals of Robotic Grasping and Fixturing. Caihua Xiong, Han
Ding, and Youlun Xiong, World Scientific Publishing Company, 2007.
ISBN-13 978-981-277-183-4, ISBN-10 981-277-183-2
Handouts and research articles may also be used by the instructor.
Objective
2. This course focuses on providing comprehensive information and
mathematic models of developing and applying grippers and fixtures in industry,
and present long term valuable essential information for the academic researchers
who are interested in robotic manipulation as a good reference.
Pre-Requisite
3. Robot Mechanics and Control
Course Outcome
4. This course will furnish the students with a comprehensive insight into
robotic grasping and fixturing. It involves study of multifigured robot hand grasp,
basic fixture design principle, and evaluating and planning of robotic
grasping/fixturing, and focuses on the modeling and applications of Robotic
Grasping and Fixturing.
Course Outline:

Allocated
Topics
Periods
Robotic Grasp and Workpiece-Fixture Systems 48
• Introduction
• Robotic Manipulation and Multifingered Robotic
Hands
• AMT and Fixtures
• Comparison between Grasping and Fixturing

Qualitative Analysis and Quantitative Evaluation of

Form-Closure Grasping/Fixturing
• Kinematic Characteristics of Grasping/Fixturing
• Discriminances of Form-Closure Grasping/Fixturing
• Minimum Number of Contacts with Frictionless
• Grasp Evaluation Criteria

Stability Index and Contact Configuration Planning

of Force-Closure Grasping/Fixturing
• Description of Contacts with Friction
• Conditions of Force Closure Grasp
• Grasp Stability Index

Active Grasp Force Planning

• Nonlinear Programming in Grasp
• Force Planning Using Neural Networks

Grasp Capability Analysis

• Evaluation of Multifingered Grasp Capability

7. RIME 814: Rehabilitative and Assistive Robotics

Textbook
1. Wearable Robots: Biomechatronic Exoskeletons by Jose Pons (Wiley
Publishers)
Handouts and research articles may also be used by the instructor.

Objective
2. A wearable robot is a mechatronic system that is designed around the shape
and function of the human body, with segments and joints corresponding to those
of the person it is externally coupled with. Tele-operation and power amplification
were the first applications, but after recent technological advances the range of
application fields has widened. These robots have to support the motion of human
limbs and are valuable in the process of rehabilitation as strength augmentation.
This course will enable the students to get an insight into the design and control
challenges of such robots.

Pre-Requisite
3. Linear Algebra, Robot Mechanics and Control

Course Outcome
4. By the end of this course the students will be well-versed in Biomechanics
and Human Interaction. Models of Bio-inspiration along with their actuation
requirements will also be introduced to the students and designof systems that
enable these motions will be focused.

Course Outline
5. The mechanics of the wearable robot and its biomechanical interaction with
the user, including state-of-the-art technologies will be covered. The basis for
bioinspiration and biomimetism, general rules for the development of
biologically-inspired designs, and how these could serve recursively as biological
models to explain biological systems and finally the incorporation of this
knowledge in the design of exoskeletons and prosthetic limbs will be taught.
Topics Allocated Periods

• Bioinspiration and Biomimetism 45

• Biological Models
• Human Machine Interfacing
• Robot Actuation
• Sensing and Instrumentation
• Compliance in Design
• Design of Rehabilitative Robots
• Design Considerations in Robot Assistance
8. RIME 835: Human-Robot Interaction

Textbook
1. Designing Sociable Robots (Intelligent Robotics and Autonomous Agents
series) by Cynthia Breazeal ISBN: 9780262025102. The course will also be
research paper based. Depending upon the module, the instructor(s) may also
assign a reference book.
Reference Books
2. • Human-Robot Interaction in Social Robotics by Hiroshi Ishiguro and
Takayuki Kanda
• Human-Robot Interactions: Principles, Technologies and Challenges.
Editor: Diana Coleman.
Pre-Requisite
3. CSE 860 Artificial Intelligence (or equivalent), Robotics, Strong
programming background.
Objective
4. This is a highly research-oriented course with the basic objective of
bringing the students face to face with the latest cutting-edge research in the
world. This will play a key role in helping them select suitable topics for their
research that would lead to publications in leading international journals and
conferences
Course Outcome
5. Students completing this course are expected to have developed a firm
knowledge base of critical understanding of the main theories, principles and
concepts relating to the domain of Human-Robot Interaction.
Course Outline
6. This course will cover a variety of topics related to social intelligence and
socially intelligent robots. Readings/lectures will cover (1) what’s known about
how this ability arises in human intelligence, and (2) state-of-the-art approaches
to building computational systems with this type of social ability.

Topics Allocated Periods

• The Vision of Sociable Robots 45
• Robot in Society: A Question of Interface
• Insights from Developmental Psychology
• Designing Sociable Robots
• The Physical Robot
• The Vision System
• The Auditory System
• The Motivation System
• The Behavior System
• Facial Animation and Expression
• Expressive Vocalization System
• 12. Social Constraints on Animate Vision

9. RIME 836: Probabilistic Robotics

Textbook
1. Probabilistic Robotics. By Sebastian Thrun, Wolfram Burgard, and Dieter
Fox, MIT Press (2006), ISBN: 978-0-262-20162-9.
Handouts and research articles may also be used by the instructor.

Objective
2. This course focuses on robot perception and control in the face of
uncertainty. Building on the field of mathematical statistics, probabilistic robotics
endows robots with a new level of robustness in real-world situations.

Course Outcome
3. This course will furnish the students with a practical experience in robot
perception in partially known environments through implementations in pseudo
code, detailed mathematical derivations, discussions from a practitioner's
perspective, and extensive lists of exercises and class projects

Course Outline:
Topics Allocated Periods
Introduction 45
• Uncertainty in Robotics
• Probabilistic Robotics
Bayes Filter
• Gaussian Filters
• Kalman Filter
• Extended Kalman Filter (EKF)
Nonparametric Filters
• Histogram Filter
• Particle Filter
Localization
• Markov Localization
• EKF Localization
• Multi-Hypothesis Tracking
 • Monte Carlo Localization
Occupancy Grid Mapping
Simultaneous Localization and Mapping
• EKF SLAM
• Graph SLAM
10. RIME 843: Sensors and Sensing

Textbook
1. Handbook of Modern Sensors. By Jacob Fraden, Springer, 2010.
ISBN-13: 978-1-4419-6465-6

Reference Books
2. Introduction to Autonomous Mobile Robots. By Roland Siegwart and Illah
R. Nourbakhsh, The MIT Press, 2004.ISBN-10: 0-262-19502-X, ISBN-13:978-
0-262-19502-7
Probabilistic Robotics. By Sebastian Thrun, Wolfram Burgard, and Dieter
Fox, MIT Press (2006)
ISBN: 978-0-262-20162-9.
Objective
3. This course focuses on various sensors used for Robot Navigation and
Control. Its objective is to teach students about sensing and modeling surrounding
environment for motion planning and navigation.

Course Outcome
4. This course will furnish the students with an understanding of the design
and working of sensors for Robotics while also teaching them about the
techniques needed for signal processing of the sensor data.

Course Outline:
Topics Allocated Periods
• Sensor Characteristics 45
• Calibration
• Accuracy
• Repeatability
• Data Acquisition from Sensors
• Odometers
• Heading Sensors
• Accelerometer
• Inertial Measurement Unit
• Vision Sensing
• Range Sensing
• Sonar Sensing
• Flow Sensing
• Touch Sensing
• Sensing for Surveillance
• People Sensing
• Multi-Sensor Fusion
11. RIME 837: Simultaneous Localization and Mapping

Textbook
1. Probabilistic Robotics. By Sebastian Thrun, Wolfram Burgard, and Dieter
Fox, MIT Press (2006)
ISBN: 978-0-262-20162-9.

Reference Book
2. Introduction to Autonomous Mobile Robots. By Roland Siegwart and Illah
R. Nourbakhsh, The MIT Press, 2004. ISBN-10: 0-262-19502-X, ISBN-13:978-
0-262-19502-7.
Handouts and research articles may also be used by the instructor.

Objective
3. This course focuses on Robot Localization and Mapping in unknown or
partially known environments.

Course Outcome
4. This course will furnish the students with practical knowledge of SLAM
algorithms required for mapping and navigation in unknown of partially known
environments.

Course Outline

Topics Allocated Periods

Introduction to the Simultaneous Localization and 45
Mapping (SLAM) Problem
SLAM with Extended Kalman Filter
• SLAM with Known Correspondences
• SLAM with Unknown Correspondences
SLAM with Particle Filter
Graph-based SLAM
Biologically-inspired SLAM Solutions
• RatSLAM
Loop-Closure in SLAM
Hierarchical SLAM
SLAM Using Vision
• Monocular SLAM
• Stereo and Multi-camera SLAM
• SLAM using Catadioptric Sensors
Underwater SLAM
SLAM for UAVs (Unmanned Aerial Vehicles)
12. RIME 817: BioRobotics

Textbook
1. Biorobotics–Methods and Applications, edited by Barbara
Webb and Thomas R. Consi.

Objective
3. The objective of this course is to develop expertise of the multidisciplinary
field of BioRobotics. The course involves detailed study of Biosignals and the
principals of Bio Mechanical Designs.

Course Outcome
4. After studying this course students will be able to use HumanNeurological
Signals for operations of various kinds of Robots. The course will also enable
students to develop Biomatic Robotic systems.

Course Outline

Topics Allocated Periods

• Introduction to biomechatronics and biorobotics. 45
• Types of biosensors and instruments.
• Modeling and design of prosthetic devices.
• Principle of electromyography (EMG).
• Design of prosthetic devices.
• Control of prosthetic devices using EMG –
preprocessing and pattern recognition.
• Control of prosthetic devices using EMG – control
command generation.
• Bio-inspired machines.
• Robotic rehabilitation.
• Brain-controlled robotics.
• Functional near-infrared spectroscopy based brain-
computer interfaces.
13. RIME 832: Machine Learning (3-0)
Textbook: Introduction to Machine Learning, by Ethem Alpaydin, MIT
Press, 2004.
ISBN-10: 0-262-01211-1, ISBN-13: 978-0-262-01211-9
Reference Book: Machine Learning, by Tom M. Mitchell, McGraw-Hill
Science / Engineering / Math; 1 edition (March 1, 1997).
ISBN-10: 0070428077, ISBN-13: 978-0070428072
Objective:
When you have completed this course, you should be able to apply machine
learning algorithms to solve both IID and sequential data problems of
moderate complexity. You should also be able to read current research
papers in machine learning and understand the issues raised by current
research in supervised learning.
Pre-Requisite:
CSE 860 Artificial Intelligence (or equivalent)
Course Outcome:
The students graduating from this course are expected to have a thorough
knowledge base of Machine Learning algorithms and methodologies as well
as their applications in robotics and machine intelligence.

Course Outline:
This course will present an introduction to algorithms for machine learning
and data mining. These algorithms lie at the heart of many leading-edge
computer applications including optical character recognition, speech
recognition, text mining, document classification, pattern recognition,
computer intrusion detection, and information extraction from web pages.
Every machine learning algorithm has both a computational aspect (how to
compute the answer) and a statistical aspect (how to ensure that future
predictions are accurate). Algorithms covered include linear classifiers
(Gaussian maximum likelihood, Naive Bayes, and logistic regression) and
non-linear classifiers (neural networks, decision trees, support-vector
machines, nearest neighbor methods). The class will also be introduced to
techniques for learning from sequential data and advanced ensemble
methods such as bagging and boosting.

Topics Allocated
Periods
Overview/Introduction to machine learning 45
Hypothesis spaces
Space of Algorithms, Linear Threshold Classifiers
Project details
Perceptrons
Logistic Regression
 Linear Discriminant Analysis
Off-The-Shelf Learning Algorithms
Decision Trees
Nearest Neighbor
Neural networks
Bayesian Learning
Support Vector Machines
Learning Theory
Learning Theory finished
Bias/Variance Theory & Ensemble Methods
Preventing Over-fitting: Penalty and Hold-out
methods
Hold-Out and Cross-validation Methods
Penalty methods: decision trees, neural nets, SVMs
Evaluating and Comparing Classifiers
Unsupervised Learning

14. EM 840: Data Acquisition and Control (3-0)

Text Book:
• Transducers and Instrumentation, D.V.S. Mury, Prentice-Hall
International, Inc.
• Digital Control System Analysis and Design by C. L. Phillips and
H. T. Nagle, Jr., 3rd edition, Prentice-Hall International Inc.
Reference Books:
• Electronics with Digital and Analog Integrated Circuits by Richard
J. Higgins Prentice-Hall International, Inc
• TMS320C3x DSP Starter Kit User’s Guide by Texas Instruments
Objective:
The objective of this course is to impart theoretical and practical
knowledge of advanced data acquisition and control to graduate students.
Course Outcome:
Students after successfully completing of this course will be able to
demonstrate:
i. Understanding of all the components required for data acquisition
systems.
ii. Knowledge of analyzing the system speed, resolution and accuracy.
iii. Knowledge of designing an efficient data acquisition system for the
required applications
iv. Knowledge to use controller design techniques to make the system
behavior satisfy specified design objectives
v. Ability to evaluate and test the system performance using digital
simulations.
Course Outline:
 Topics Allocated
Periods
1. Introduction to Data acquisition 45
2. Passive and Active Electrical Transducers
3. Signal Conditioning Circuits
4. Digital Interfacing
5. Data Communication and Networks
6. ADC and DAC, Timers and Counters
7. Digital measurements and control programming for
real time
systems
8. Introduction to Digital Control Systems
9. Digital Controller Design

15. RIME 914: Robot Motion Planning (3-0)

Textbook: Planning Algorithms by Steven M. LaValle, Cambridge
University Press, 2006.
ISBN-10: 0521862051, ISBN-13: 978-0521862059
Reference Book: Robot Motion Planning, By Jean-Claude Latombe,
Kluwer Academic
Publishers. ISBN-10: 079239206X, ISBN-13: 978-0792392064
Objective:
The aim of this course is to teach the students about advanced techniques
used for robot motion planning. The course combines the knowledge of
robotics with that of artificial intelligence and control theory to give the
students a practical overview of the cutting-edge methods used in the area
of planning algorithms.
Pre-Requisite:
EM 800 Robotics – I (or equivalent)
Course Outcome:
Students completing this course are expected to possess a firm grasp of
robot motion planning algorithms.
Course Outline:
The course can broadly be outlined as motion planning, decision theoretic
planning and planning under differential constraints.
Topics Allocated Periods
Discrete Planning 45
Logic Based Planning Methods
 Configuration Space
Sampling Based Motion Planning
Combinatorial Motion Planning
Time Varying Problems
Mixing Discrete and Continuous Spaces
Planning for Closed Kinematic Chains
Feedback Motion Planning
Basic Decision Theory
Sequential Decision Theory
Sensors and Information Spaces
Planning under Sensory Uncertainty
Differential Models
Sampling Based Planning under Differential
Constraints
System Theory and Analytical Techniques

16. RIME 933: Advanced AI/Special Topics in Artificial Intelligence (3-0)

(Any subject on the research interest of the faculty available)
Textbook: The course will mainly be research paper based. Depending
upon the module, the instructor(s) may also assign a reference book.
Objective:
This is a highly research-oriented course with the basic objective of bringing
the students face to face with the latest cutting edge research inthe world.
This will play a key role in helping them select suitable topicsfor their
research that would lead to publications in leading international journals and
conferences.
Pre-Requisite:
CSE 860 Artificial Intelligence (or equivalent)
Course Outcome:
Students graduating from this course are expected to develop a deep insight
into cutting edge artificial intelligence technologies with an overview ofthe
underlying theory and methodologies in each subject area. This course will
be very helpful for students to take up research theses of good technical
value in the cutting edge research areas.
Course Outline:
The course will comprise several modules, each of which would cover one
of the cutting edge research topics. Depending upon the interest of the class
and the ongoing research projects in the department, some of the following
research topics will be taught about. The instructors may add or amend
research subjects depending upon the orientation of the class.
 Topics Allocated
Periods
Brain simulation 45
Nouvelle AI
Embodied AI
Situated AI
Behavior based AI
Embodied Embedded Cognition
Embodied cognitive science
Computational intelligence (CI)
Evolutionary algorithms
Swarm intelligence
Artificial Immune Systems
Immunocomputing
Speech Processing and Synthesis

17. AI 813: Multi-agent Systems

Textbook
• Shoham, Y. & Leyton-Brown, K. (2009). Multiagent Systems: Algorithmic,
Game-Theoretic, and Logical Foundations. The book is available at
http://www.masfoundations.org/
• Handouts and research articles may also be used by the instructor.

Objective
Multiagent systems (MAS) can be defined as loosely coupled networks of
problem solvers that interact to solve problems that are beyond the individual
capabilities or knowledge of each problem solver. These problem solvers, often
called agents, are autonomous and can be heterogeneous in nature.

Research and development in MAS are concerned with the study and
construction of a collection of autonomous agents that interact with each other
and their environments. The study of such systems goes beyond the study of
individual intelligence in its consideration of problem solving with social
components.

This course introduces the students to the main topics in the theory and practice
of MAS, currently one of the most important and rapidly expanding areas of
computer science, having emerged from the study of distributed artificial
intelligence (DAI). Multiagent systems have been used as an important means
with which to address the development of large and complex information systems
(IS) and decision support systems (DSS). Finally, this course introduces
coalitional game theory and its potential applications.
Pre-Requisite
The student should be comfortable with mathematical notation and basic
computer algorithms

Course Outcome
During the course, students will learn to:

• Demonstrate/explain the basic concepts of agent-based approach, non-

cooperative game theory, multiagent learning, social choice, mechanism
design, auctions, and cooperative game theory;
• Develop business and real-world perspectives of multiagent systems;
• Use software tools to develop and test multiagent systems;
• Be aware of future and current trends in MAS research and applications.
Course Outline

Allocated
Topics
Periods
• Foundations 45
• Intelligent Agents and Multiagent Systems
• Multiagent Learning
• Social Choice
• Mechanism Design
• Multiagent Resource Allocation
• Coalition Game

18. AI 803: Mathematics for Artificial Intelligence

It’s a rather unique course offered as core in our medical institution. We expect
that the usual rantings from the faculty regarding mathematical inadequacy of
student cohorts would go down with the introduction of this course at the grad
level.
Recommended Books:
1. Linear Algebra and Learning from Data, Gilbert Strang, Wellesley-
Cambridge Press, 2019.
2. Math for Machine Learning: Open Doors to Data Science and Artificial
Intelligence, Richard Han, CreateSpace Independent Publishing Platform,
2018.
3. Machine Learning: A Probabilistic Perspective, Kevin Murphy, The MIT
Press, 2012.
Credit Hours: 3 (3, 0)
Course Objectives:
• To understand the basic mathematics, such as linear algebra and calculus,
that is behind many aspects of vision, text processing, and machine
learning.
• To understand the basic statistics that can be used in image processing and
learning.
Allocated
Topics / Contents
Periods
The course would cover basic aspects of linear algebra such
as scalars, vectors, matrices, and tensors. It would then move
on to different matrix operations and discuss eigen values and
eigen vectors. It would also discuss matrix decomposition, 45
such as SVD and eigen decomposition. Multivariable
calculus would start with the basic concepts of derivates
(both first and second order), integration for both discrete and
continuous variables, gradient descent and optimization.
Probability and statistics would cover topics such as random
variables, expected value, variance, different probability
distributions, and central limit
theorem.

19. AI 917: Evolutionary Algorithms

Since the publication of Darwin’s magnum opus, The Origin of Species in 1859,
and the ensuing coining of the term the survival of the fittest, the word evolution
has pervaded different disciplines and AI is no exception. In fact ithas been
observed that certain kind of learning cannot take place within one generation and
can only be done over many generations by evolving better individuals through
the genetic processes. When the computer scientists got cognizant of the concept,
a whole new field of evolutionary computation arose, and now many problems in
CS are only seen in this context.
Recommended Books:
1. Evolutionary Algorithms, Alain Petrowski, Sana Ben-Hamida, John Wiley
& Sons, Inc., 2017.
2. Evolutionary Optimization Algorithms, Dan Simon, John Wiley & Sons,
Inc., 2013.
3. Evolutionary Algorithms, Swarm Dynamics and Complex Networks:
Methodology Perspectives and Implementation, Ivan Zelinka, Guanrong
Chen (Editors), Springer, 2018.
Credit Hours: 3 (3, 0)
Course Objectives:
• To formulate and represent a problem as an evolutionary computation
problem.
• To implement and assess different evolutionary algorithms.
• To formulate single and multiple objectives functions.
Allocated
Topics / Contents
Periods
The topics include evolutionary computation, genetic
algorithms, evolution strategies, evolutionary programming,
genetic programming, constraint handling, evolutionary
neural networks, co-evolution, and swarm intelligence. Other 45
topics include genotypes and phenotypes, schema theorem,
convergence velocity perspective, multi-objective functions,
self-adaptation in genetic algorithms, and their
optimization.

20. RIME 942: Pattern Recognition

It is another name for machine learning but offers a different perspective. The
term has its origins in EE as compared to machine learning which has its origin
in CS. It has a more mathematical icing with the underpinning mathematical
concepts and terms discussed in detail to bring students up-to-date on thiscrucial
aspect.
Recommended Books:
1. Pattern Recognition and Machine Learning, revised edition, Christopher
M. Bishop, Springer, 2016.
2. Pattern Recognition and Classification: An Introduction, GeoffDougherty,
Springer, 2013.
Pattern Classification, 2nd edition, Richard O. Duda, Peter E. Hart, David G.
Stork, John Wiley & Sons, Inc., 2001
Credit Hours: 3 (3, 0)
Course Objectives:
• To understand what a pattern is and the basics of what intelligence and
learning are.
• To understand feature extraction, their evaluation, and selection.
• To use supervised and unsupervised approaches for identification of
patterns in the ata.
Allocated
Topics / Contents
Periods
The topics include Bayesian decision theory, Bayesian
networks, maximum likelihood estimation, dimensionality
reduction, feature selection, Bayesian estimation, linear
discriminant functions, Support vector machines, 45
expectation maximization algorithm, and non-parametric
estimation. Other topics include string matching, bias and
variance, bagging and boosting, and unsupervised learning
and clustering.

21. AI 814: Knowledge representation and reasoning

Many modern systems where NLP is used for exploring patterns in the data, or
in the cases where multimedia including text is considered, it becomes important
to see relationships between different objects and patterns. Thus,ontologies need
to be built for reasoning and knowledge representation becomes the key to it.
Recommended Books:
1. Knowledge Representation and Reasoning, 3rd edition, Gerardus Blokdyk,
Emereo Pty Limited, 2018.
2. Knowledge Representation and Reasoning with Deep Neural Networks,
Arvind Ramanathan Neelakantan, University of Massachusetts Libraries,
2017.
3. Knowledge Representation and Reasoning, Ronald Brachman, Hector
Levesque, Elsevier, 2004.
Credit Hours: 3 (3, 0)
Course Objectives:
 • To understand what representation is for knowledge.
• To use logic (both propositional and first order) for representation.
• To understand how reasoning can be done in logic, and what entailment
is.
• To understand the theory and principles of automated theorem proving.
• To get acquainted to tools that can be used for knowledge representation
and reasoning.
Allocated
Topics / Contents
Periods
Topics include propositional logic, its syntax and semantics.
Proof by resolution and automated theorem proving. First-
order logic, its syntax and semantics. Forward and backward
chaining. Semantic nets. Inheritance in taxonomies. Other 45
topics include other approaches and issues (e.g. predicate
logic, fuzzy logic, week and strong slot and filler
structures), knowledge acquisition, the frame problem,
symbolic reasoning under uncertainty (nonmonotonic
reasoning, augmenting a problem Solver), statistical
reasoning (e.g. probability and Bays Theorem, Bayesian
networks, Dumpster-Shafer theory), building
knowledge-based systems.

22. AI 844: Semantic Web

Semantics is derived from the context, and anywhere where context is being used
to identifya word, it falls under semantics. Within the ambit of semantic web it
includes information in various forms, such as images and pictures, structured and
unstructured information, and videos.
Recommended Books:
1. Semantic Web Science and Real-World Applications, Lytras, Miltiadis
D., Aljohani, Naif, Damiani, Ernesto, IGI Global, 2019.
2. Semantic Web-Based Systems: Quality Assessment Models, Sandeep
Kumar, Niyati Baliyan, Springer 2018.
3. Semantic Web: Ontology and Knowledge Base Enabled Tools,
Services, and Applications, Amit Sheth, Information Science
Reference, 2013.
Credit Hours: 3 (3, 0)
Course Objectives:
• To understand the technical architecture of the semantic web and how it
integrates with the traditional World Wide Web.
• To understand the underlying representations of information and do
inference on them.
• To be able to use common semantic web tools to design, implement, and
verify ontologies.
Allocated
Topics / Contents
Periods
The topics include RDF and linked data, ontologies, the RDF
query language SPARQL, RDF triplestores, understanding
datasets, basic OWL modeling, creating an ontology from
given requirements, Ontology Design Patterns (ODPs), ODP 45
based modeling, description logics, ontology-alignment and
debugging, constraints in RDF, data quality, and data
cleaning in RDF.

23. EM 890: Modeling and Simulation

Mathematical modeling and its simulation is the key to understanding where the
system will be successful and where it will fail to perform as per the requirement.
Not every scenario can be generated in the lab environment and tested for its
efficacy. In most of the cases it is much cheaper to first simulate it and only
prototype it once it has been deemed to be workable.
Recommended Books:
1. Theory of Modeling and Simulation: Discrete Event & Iterative System
Computational Foundations, Bernard P. Zeigler, Alexandre Muzy,Ernesto
Kofman, Elsevier Science, 2018.
2. Modeling and Simulation: An Application-Oriented Introduction, Hans-
Joachim Bungartz, Stefan Zimmer, Martin Buchholz, Springer, 2014.
3. Modeling and Simulation of Complex Systems: A Framework for Efficient
Agent-Based Modeling and Simulation, Robert Siegfried, Springer
Vieweg, 2014.
Credit Hours: 3 (3, 0)
Course Objectives:
• To understand what problems may be most suitable to be modeled and
simulated as opposed to being physically implemented.
• To understand parameters and constraints that may define the scope of the
problem to be modeled and simulated.
• To be able to demonstrate coding and implementation skills in the available
tools to simulate some real-world problem, which is not easily expressed
using mathematics.
Allocated
Topics / Contents
Periods
Course contents include topics on system analysis,
classification of systems, and system theory basics and its
relevance to simulation. For modeling the course includes
model classification which refers to conceptualization, 45
abstraction, and simulation of the models. It also includes
topics related to simulation systems and languages. It also
covers topics such as Petri nets and finite automata and
their use in representing models. Both discrete and
continuous systems are covered. For continuous systems,
numerical methods are included. For testing, validity and
verification of models is discussed. Optimization is alsomade
part of it so that the developed systems are optimized
as per the set criteria.

24. AI 822: Advanced Image Processing

Image processing underpins computer vision. No mentionable work can be done

in vision without proper grounding in image processing. Even students who
have already taken this course at the under-grad level are not familiar with the
techniques that fall in the advanced category. It would be useful for both first time
and experienced students. It is not offered by any of the universities we have
compared our program with but we feel that its inclusion is essential for us.
Recommended Books:
1. Advanced Image and Video Processing Using Matlab, Shengrong Gong,
Chunping Liu, Yi Ji, Springer, 2019.
2. Hands-On Image Processing with Python: Expert techniques for advanced
image analysis and effective interpretation of image data, Sandipan Dey,
Packt Publishing, 2018.
3. Principles of Digital Image Processing: Advanced Methods, Wilhelm
Burger, Mark J. Burge, Springer, 2013.
Credit Hours: 3 (3, 0)
Course Objectives:
• To introduce students to advanced theoretical concepts.
• To develop in students the problem solving skills and build in them
engineering intuition.
• To inculcate practical skills and know how to be able to build working
computer vision based systems.
Allocated
Topics / Contents
Periods
The topics include color, camera models and calibration,
scale in image processing, line and corner detection, and
maximally stable extremal regions. It also includes topics
related to mathematical morphology such as binary, gray- 45
scale, skeletonization, granulometry, and morphological
segmentation. It would also cover image compression,
texture, and image registration including rigid, non-rigid, and
RANSAC.

25. AI 843: Natural Language Processing

NLP is one of the main tasks where AI is the key underlying technology.
Processing text in main cases is the main problem to be solved specially when
data is available in that form, and also when robots have to communicate with
humans they may resort to it. Also, its coupling with the speech processing unit
would give extra leverage to the robots to do their tasks in a more effective
manner.
Recommended Books:
1. Natural Language Processing Recipes: Unlocking Text Data withMachine
Learning and Deep Learning using Python, Akshay Kulkarni, Adarsha
Shivananda, Apress, 2019.
2. Deep Learning in Natural Language Processing, Li Deng, Yang Liu
editors, Springer 2018.
3. Python Natural Language Processing, Jalaj Thanaki, Packt Publishing,
2017.

Credit Hours: 3 (3, 0)

Course Objectives:
• To understand vector space models and use of context to derive semantics.
 • To understand modern deep learning based algorithms that are used for
NLP.
• To be able to process large unstructured and unlabeled text to extract
useful information.
Allocated
Topics / Contents
Periods
The course covers topics such as word vectors, word senses,
neural networks and matrix calculus, backpropagation and
computational graphs, linguistic structure dependency and
parsing, recurrent neural networks and language models, 45
vanishing gradients and fancy RNNs, machine translation,
question answering, ConvNets for NLP, subword models,
generative models, safety, bias, and fairness. Other topics
include words, morphology, and lexicon, noisy channel
models and edit distance, classification, parts of speech tags,
hidden markov models, Chomsky hierarchy and natural
language, context- free recognition, lexical semantics, word
sense
disambiguation, and interpreting social media.

26. AI 831/937: Intelligent Systems

Intelligent system relates to planning, execution, and learning and is essential for
us due to the nature of robotics that we are going to do where all the three aspects
above would be covered.
Recommended Books:
1. Learning and Execution of Object Manipulation Tasks on Humanoid
Robots, Waechter, Mirko, Scientific Publishing, 2018.
2. Machine Learning Methods for Planning, Steven Minton, Elsevier Science,
2014.
3. Using Neural Networks and Dyna Algorithm for Integrated Planning,
Reacting and Learning in Systems, National Aeronautics and Space Adm
Nasa, Independently Published, 2018.
Credit Hours: 3 (3, 0)
Course Objectives:
• To comprehend the challenges in developing autonomous systems oragents
that plan, execute, and learn from the consequences of their actions.
 • To understand what planning is, how it is represented, how it is evaluated,
and how it is learned.
• To implement a simple complete system which shows autonomous
behavior.
Allocated
Topics / Contents
Periods
The topics include closed-world assumption, linear
programming, GPS algorithm, prodigy algorithm, S-Space
transformation, constructing graphs of the planning
problem, Planning graphs for planning and heuristic search, 45
A* and weighted A* search, multi-heuristic A*, probabilistic
path planning, planning under uncertainty, reinforcement
learning, experience graphs, learning in planning, deep
reinforcement learning, learning cost functions, multi-agent
decision making, and short-sighted
probabilistic planning.

27. AI 851 Advanced Signal Processing(3, 0)

Pre-requisite: None
Recommended Books:
1. Advanced Digital Signal Processing and Noise Reduction, Saeed V.
Vaseghi, John Wiley & Sons, Limited, 2020.
2. Digital Signal Processing using Matlab, 3rd edition, Robert J. Schilling,
Sandra L Harris, Cencage Learning, 2017.
3. Bayesian Signal Processing, 2nd edition, James V. Candy, John Wiley &
Sons, Inc., 2016.
Credit Hours: 3 (3, 0)

Course Objectives:
• To be able to use Fast Fourier Transform in a variety of applications such
as signal analysis, fast convolution, spectral and temporal interpolation, and
filtering.
• To understand how to design digital filters.
• To be able to construct a simple digital communication system.
Allocated
Topics / Contents
Periods
The topics include digital systems and signals, impulse
response, frequency response, discrete-time Fourier
transform, z-transform, interpolation and decimation,
sample rate changes, polyphase decomposition, random
signals and vectors, joint random signals and their statistical 45
description, Stationarity and ergodicity, Linear systems with
stationary random inputs, Power spectral density, Metric
spaces, vector spaces, normed vector spaces, inner projects
and inner-product spaces, Hilbert spaces, Projections,
Orthogonality, Orthogonalization of vectors, Approximation
in Hilbert spaces, The orthogonality principle, Least squares
filtering, Linear prediction and AR spectrum estimation,
MMSE estimation and MMSE filtering, Weiner filtering,
Signal transformation and generalized Fourier series, Scaling
functions and wavelets, Wavelet transform and its
implementation, Eigenvalues and linear systems/operators,
Diagnolization of a matrix, Karhunen-Loeve expansion,
Principal component analysis, Pisarenko harmonic
decomposition, MUSIC, SVD and applications, Applications
of adaptive filtering, LMS
algorithm, RLS algorithm.

28. AI 841 Data Mining (3, 0)

Pre-requisite: None
Recommended Books:
1. Introduction to Data Mining, Pang-Ning Tan, Michael Steinbach, Anuj
Karpatne and Vipin Kumar, 2nd Edition, Pearson, 2018.
2. Principles of Data Mining, 3rd edition, Max Bramer, Springer, 2016.
3. Mining of Massive Datasets, 2nd edition, Jure Leskovec, Anand
Rajaraman, Jeffrey David Ullman, Cambridge University Press, 2014
Credit Hours: 3 (3, 0)
Course Objectives:
• To determine whether a particular problem is a data mining problem or
not.
• To understand the complete lifecycle of a datamining process such as
data preparation, modeling, and evaluation.
• To pose a problem as a data mining problem, implement and evaluate it.
Allocated
Topics / Contents
Periods
This course provides both theoretical and practical coverage
of all data mining topics. The topics include: Overview of
Data Mining, Data Preprocessing, OLAP and data 45
generalization, Data Cube Computation and
Multidimensional Data Analysis, Mining Frequent Patterns,
Associations, and Correlations, Classification, Cluster
Analysis, Outlier Detection, Anomaly Detection; Avoiding
False Discoveries.

29. AI 842 Information Retrieval (3, 0)

Pre-requisite: None
Recommended Books:
1. Learning to Rank for Information Retrieval, Tie-Yan Liu, Springer Berlin
Heidelberg, 2014.
2. Multilingual Information Retrieval: From Research to Practice, Carol
Peters, Martin Braschler, Paul Clough, Springer, 2012.
3. Modern Information Retrieval. Baeza-Yates Ricardo and Berthier
Ribeiro-Neto. 2nd edition, Addison-Wesley, 2011.
Credit Hours: 3 (3, 0)
Course Objectives:
• Introduce the concepts underlying technologies of modern information
retrieval systems.
• To study theoretical aspects as well as implementation issues of classical
and modern retrieval problems such as search engines.
• Basic and advanced techniques for building text-based information
systems
Allocated
Topics / Contents
Periods
This course provides a variety of basic principles, techniques
and modern advances for searching, managing, and mining
information. It will cover algorithms, design, and 45
implementation of modern information retrieval systems.
The topics include: Search engine architecture, Retrieval
models, Retrieval evaluation, Relevance feedback, Link
analysis, Search applications, Retrieval system design and
implementation, text analysis techniques, retrieval models
(e.g., Boolean, vector space, probabilistic, and learning-
based methods), search evaluation, retrievalfeedback, search
log mining, and applications in web information
management. IR techniques for the web,
including crawling, link-based algorithms, and metadata
usage are also discussed

30. AI 815 Neural Networks (3, 0)

Pre-requisite: None
Recommended Books:
 1. Make Your Own Neural Network: A Gentle Journey Through the
Mathematics of Neural Networks, and Making Your Own Using thePython
Computer Language, Tariq Rashid, CreateSpace Independent Publishing
Platform, 2016.
2. Neural network design, 2nd edition, Martin T. Hagan, Howard B. Demuth,
Mark Hudson Beale, Martin Hagan, 2014.
3. Neural Networks with R: Smart models using CNN, RNN, deep learning,
and artificial intelligence principles, Giuseppe Ciaburro, Balaji
Venkateswaran, Packt Publishing, 2017.
Credit Hours: 3 (3, 0)
Course Objectives:
• To introduce the neural networks for regression and classification.
• To give different approaches that can be used to design a neural network
based solution.
• To understand how weights are learned and how over-fitting is avoided.
• To demonstrate implementation of neural networks on available tools.
• To demonstrate conception, designing, and solution of real world
problems using neural networks.
Allocated
Topics / Contents
Periods
The topics include the neuron models and basic learning
rules, the learning of a single neuron and a single-layered
neuron, multilayer neural networks and backpropagation, 45
associative memory, self-organizing feature map, RBF
neural networks and support vector machines, and neural
network trees.

31. AI 853 Advanced Programming in Python (3, 0)

Pre-requisite: None
Recommended Books:
1. Advanced Python Programming: The Insider Guide to Advanced Python
Programming Systems, Richard Ozer, Python Programming, CreateSpace
Independent Publishing Platform, 2017.
2. Introduction to Machine Learning with Python: A Guide for Data Scientists
1st Edition, Andreas C. Müller, Sarah Guido, 2016.
3. Fluent Python: Clear, Concise, and Effective Programming 1st Edition,
Luciano Ramalho, 2015
Credit Hours: 3
Course Objectives:
• To be able to add enhancements to classes.
 • To implement and run unit tests.
• To create multi-threaded and multi-process applications.
Allocated
Topics / Contents
Periods
The topics include Advanced List Comprehensions,
Collections Module, Mapping and Filtering, Lambda
Functions, Advanced Sorting, Unpacking Sequences in 45
Function, Calls, Modules and Packages, Working with Data,
Databases, CSV, Getting Data from the Web, HTML, XML,
JSON, Testing and Debugging, Creating Simulations,
Testing for Performance, The unittest Module, Classes and
Objects, Creating Classes, Attributes, Methods
and Properties, Extending Classes, Documenting Classes,
Static, Class, Abstract Methods, Decorator.

32. AI 854 Analysis and Visualization (3, 0)

Pre-requisite: None
Recommended Books:
1. Data Analysis and Visualization Using Python: Analyze Data to Create
Visualizations for BI Systems, Dr. Ossama Embarak, Apress, 2018.
2. Python: Data Analytics and Visualization, Phuong Vo.T.H, Martin
Czygan, Ashish Kumar, Packt Publishing, 2017.
3. R: Data Analysis and Visualization, Tony Fischetti, Brett Lantz, Jaynal
Abedin, Hrishi V. Mittal, Bater Makhabel, Edina Berlinger, Ferenc Illes,
Milan Badics, Adam Banai, Gergely Daroczi, Packt Publishing, 2016.
Credit Hours: 3 (3, 0)
Course Objectives:
• To be able to design and critique different visualizations.
• To appreciate the importance of data analytics for visualization.
• To understand the components involved in visualization and also how
different data types impact visualization.
Allocated
Topics / Contents
Periods
The course covers topics such as data processing and big
data, data understanding, data preparation, modeling,
evaluation, and analytic techniques. Regarding data the 45
topics included are importance of context, audience’s
attention, and dissecting model visuals. Predictive modeling
includes topics such as linear regression, classification, and
clustering. Topics covered related to modeling include
overfitting, generalization, plain accuracy and its problems,
confusion matrix, unbalanced classes, and unequal costsand
benefits. Topics related to visualizing model performance
include ranking, ROC graphs and curves, and AUC. Other
topics include visual encoding, bar chart and pie chart, line
chart, highlight tables, scatter plot and trend lines, heatmap,
geographic mapping, bullet graph, Gantt chart, and circle
view. It also includes table calculation,
forecast, log distribution, reference line and table.

33. AI 823 Speech Processing (3, 0)

Pre-requisite: None
Recommended Books:
1. Audio and Speech Processing with MATLAB, Paul Hill, Taylor &
Francis Incorporated, 2018.
2. Language and Speech Processing, Joseph Mariani (Editor), John Wiley &
Sons, Inc., 2013.
3. Multilingual Speech Processing, Tanja Schultz, Katrin Kirchhoff,
Elsevier, 2006.

Credit Hours: 3
Course Objectives:
• To understand the basic principles of speech perception.
• To understand basic principles of speech recognition, synthesis, and
dialogue.
• To be able to generate speech datasets and build applications to recognize
speeches and speakers.
Allocated
Topics / Contents
Periods
The topics include physical and physiological acoustics,
perception of speech, phonetics and phonology, signal
processing, speech synthesis, prosody and emotions, hidden 45
markov models, language modelling, human-computer
communication, and dialogue systems. Other topics include
linear-predictive model, cepstral analysis, speech coding,and
parameterization of DTW.

34. AI 945 Big Data Analysis (3, 0)

Pre-requisite: None
Recommended Books:
 1. Big Data Analytics: Methods and Applications, Saumyadipta Pyne, B.L.S.
Prakasa Rao, S.B. Rao, Springer, 2016.
2. Big Data Science & Analytics: A Hands-On Approach, Arshdeep Bahga,
Vijay Madisetti, VPT, 2016.
3. Data Science and Big Data Analytics: Discovering, Analyzing, Visualizing
and Presenting Data, EMC Education Services, John Wiley &Sons, 2015.
Credit Hours: 3 (3, 0)
Course Objectives:
• To introduce the concepts and algorithms used for Big Data analytics;
• To introduce the principles of the Hadoop, MapReduce and HBase.
• To enable the students to implement big data technologies
Allocated
Topics / Contents
Periods
Topics include: overview of Big data, Using Big Data in
Businesses such as big data in marketing, analytics, retail,
hospitality, consumer good, defense etc., Technologies for 45
Handling Big Data such as Hadoop, functioning of Hadoop,
Cloud computing (features, advantages, applications) etc,
Understanding Hadoop Ecosystem includes HDFS,
MapReduce, YARN, HBase, Hive, Pig,Sqoop, Zookeeper,
Flume, Oozie etc., Dig Deep to understand the fundamental
of MapReduce and HBase, Understanding Big Data
Technology Foundations that isdata source layer, ingestion
layer, source layer, security layer, visualization layer,
visualization approaches etc. Databases and Data
Warehouses, Using Hadoop to store data, Learn to Process
Data using Map Reduce, Testing and Debugging Map
Reduce Applications, Learn Hadoop YARN Architecture,
Exploring Hive, Exploring Pig, Exploring Oozie, Learn
NoSQL Data Management, Integrating R and Hadoop and
Understanding Hive in
Detail.

35. AI 855 Cyber Security (3, 0)

Pre-requisite: None
Recommended Books:
1. Computer and Cyber Security: Principles, Algorithm, Applications, and
Perspectives, Brij Gupta, Haoxiang Wang, Taylor & Francis Incorporated,
2018.
 2. Cybersecurity for Beginners, Raef Meeuwisse, Cyber Simplicity Limited,
2017.
3. Smart Cities Cybersecurity and Privacy, Danda B. Rawat, Kayhan Zrar
Ghafoor, Elsevier Science, 2018.
Credit Hours: 3 (3, 0)
Course Objectives:
• To be able to understand different kinds of cyber security threats and tell
how to counter them.
• To understand the mechanism of protecting confidentiality and
completeness of data.
• to be able to evaluate the outcome of any counter measure to mitigate
threat.
Allocated
Topics / Contents
Periods
The course starts with cyber security fundamentals
discussing in detail cyberspace, cyber security, and what a
hacker is. It goes on to discuss different types of malware 45
such as worms, viruses, spyware, and trojans. For cyber
security breaches it discusses phishing, identity theft,
harassment, and cyberstalking. Among types of cyber attacks
it will discuss password attacks, denial of service attacks,
passive attacks, and penetration testing. Among prevention
tips it would cover two-step verification and legitimacy of
websites. It would also discuss different aspects of mobile
and social network security. It wouldfinish off with details of
different prevention software such as firewalls, virtual
private networks, anti-virus and anti-
spyware, and routine updates.

36. AI845 Internet of Things(3, 0)

Pre-requisite: None
Recommended Books:
1. Internet of Things: Principals and Paradigms by Rajkumar Buyya, Amir
Vahid Dastjerdi, 1st Edition, Morgan Kaufmann, 2016.
Credit Hours: 3 (3, 0)
Course Objectives:
On completion of the course, the student should be able to:
• Explain in a concise manner how the general Internet as well as Internet
of Things work.
 • Understand constraints and opportunities of wireless and mobile networks
for Internet of Things.
• Use basic measurement tools to determine the real-time performance of
packet based networks.
• Analyse trade-offs in interconnected wireless embedded sensor networks.
Allocated
Topics / Contents
Periods
Introduction of Internet-of-Things, applications in various
domain: smart buildings, healthcare, agriculture, urban
infrastructure, transportation, assistive tracking for the blind, 45
fundamental design issues for the future Internet, differences
between Internet and Internet-of-things, design issues of
Internet-of-Things, research challenges, primer on TCP/IP
stack, wireless network protocol, medium access control,
comparative study of ZigBee, bluetooth, ultro wide band
(UWB), IEEE 802.11 a/b/g, Wi-Fi, RFID, capillary
networks: data aggregation, 6LowPAN architecture, routing
protocol in lossy networks (RPL): performance analysis and
evaluation in TinyOS, directed acyclic graph (DAG)
construction, parent-child relationship, objective function,
minimum rank with hysteresis, constrained application
protocol (CoAP).

37. AI828 Complex Adaptive Systems (3, 0)

Pre-requisite: None
Recommended Books:
Complex and Adaptive Dynamical Systems: A Primer (2011), by Claudius Gros,
Springer, 2nd Edition.
Complexity: A Guided Tour (2011), by Melanie Mitchell, Oxford University
Press, 1st Edition.
Credit Hours: 3 (3, 0)
Course Objectives:
On completion of the course, the student should be able to:
• Explain a comprehensive, clear and accessible outline to the new area of
complex adaptive systems and its application in different areas.
• Understand about the dynamics of cooperation and competition, looking
at how and why agents work together to create local patterns of
organization.
• Understand the process of self-organization and answer the big questions
about how do we get and sustain ordered patterns out of randomness and
chaos?
 • Explain the process of evolution as a powerful and relentless force that
shapes complex adaptive systems on the macro scale.
Allocated
Topics / Contents
Periods
Complex adaptive systems (CAS) are a broad class of
systems consisting of multiple interacting adaptive agents.
These systems, which span a wide range of disciplines,have 45
a number of characteristics in common. They are large
distributed systems consisting of many self-similar
components that interact and adapt. These interactions
among the distributed components are self-organizing and
produce emergent collective behavior in the system as a
whole. CAS tend to be difficult to analyze using traditional
analytical models. Agent-based models have been shown to
be effective methods for studying CAS. This course will
introduce the basic definitions of CAS, discuss examplecases
of CAS and their features, and implement and analyze
computational simulations of CAS. The content include,
Overview of CAS, Properties of CAS, Cellular automata,
Social systems, Evolution of cooperation, Emergence, Self-
organization, Swarm Intelligence, Social networks

38. AI 819 Text Analytics (3, 0)

Pre-requisite: None
Recommended Books:
Mining Text Data, by Charu C. Aggarwal and ChengXiang Zhai, Springer,
2012.
Foundations of statistical natural language processing, by Manning,
Christopher D., and Hinrich Schütze. MIT press, 1999.
Speech & Language Processing, by Dan Jurafsky and James H Martin, Pearson
Education India, 2000.
Introduction to Information Retrieval (2007), by Christopher D. Manning,
Prabhakar Raghavan, and Hinrich Schuetze, Cambridge University Press, 2007.
Applied Text Analysis with Python (2018), by Benjamin Bengfort, Tony Ojeda
and Rebecca Bilbro, O'Reilly Media.
Credit Hours: 3 (3, 0)
Course Objectives:
On completion of the course, the student should be able to:
• have a basic and hands-on understanding of the currently used frameworks
and methods for text analytics and natural language understanding, in
particular the application of machine learning methods to text analytics.
 Allocated
Topics / Contents
Periods
Given the dominance of text information over the Internet,
mining high-quality information from text becomes
increasingly critical. The actionable knowledge extracted 45
from text data facilitates our life in a broad spectrum of areas,
including business intelligence, information acquisition,
social behavior analysis and decision making.In this course,
we will cover important topics in text miningincluding: basic
natural language processing techniques, document
representation, text categorization and clustering, document
summarization, sentiment analysis, social network and
social media analysis, probabilistic topic
models and text visualization.

39. AI846 Computational Creativity (3, 0)

Pre-requisite: None
Recommended Books:
Computational Creativity: The Philosophy and Engineering of Autonomously
Creative Systems (2019), by Tony Veale, F. Amílcar Cardoso, Springer, 1st
Edition, Kindle Edition
Computational Creativity Research: Towards Creative Machines (2015), by by
Tarek R. Besold, Marco Schorlemmer, Alan Smaill, Atlantis Press, 2015 Edition.
Creative Environments: Issues of Creativity Support for the Knowledge
Civilization Age, by Andrzej P. Wierzbicki, Yoshiteru Nakamori, Springer,
2007th Edition
Credit Hours: 3 (3, 0)
Course Objectives:
On completion of the course, the student should be able to:
• become familiar with the literature on Computational Creativity.
• become familiar with the state of the art in Computational Creativity.
• acquire experience in designing an Interactive/Autonomous Creative
technique or tool.
• construct a program or computer capable of human-level creativity.
• better understand human creativity and to formulate an algorithmic
perspective on creative behavior in humans.
• design programs that can enhance human creativity without necessarily
being creative themselves.

Allocated
Topics / Contents
Periods
Computational creativity is a multidisciplinary field thatlies
at the intersection of artificial intelligence, cognitive
psychology, philosophy, and the arts. The field is concerned 45
with the theoretical and practical issues in the study of
creativity. This course is about Computational Creativity
with a focus on modeling/discovery & design/invention.
Contents of the course include, human creativity,information
processing theories of human creativity, interactive tools for
augmenting and amplifying human creativity, design of
autonomous creative systems for
creative tasks.

40. AI 837 Intelligent Transportation Systems (3, 0)

Pre-requisite: None
Recommended Books:
Sussman, Joseph. Perspectives on Intelligent Transportation Systems (ITS).
New York, NY: Springer, 2010.
Mashrur A. Chowdhury, and Adel Sadek, Fundamentals of Intelligent
Transportation Systems Planning, Artech House, Inc., 2003.
Pradip Kumar Sarkar, Amit Kumar Jain, Intelligent Transport Systems, PHI
learning, 2018.
Credit Hours: 3 (3, 0)
Course Objectives:
On completion of the course, the student should be able to:
• explain transport telemetric and its increasing significance in transportation
planning and management.
• explain scope of transport issues, such as, traffic safety, public transport,
advanced vehicle management and control.
• explain the application of information technology and telecommunications
to control traffic, inform travelers and drivers, operate public transport,
automating payments, handle emergencies and incidents, operate
commercial fleets and freight exchange, and automate driving and safety.
Allocated
Topics / Contents
Periods
Specific topics to be covered in the course include:
Identification of transportation problems and costs,
45
Definition and role of Intelligent Transportation Systems,
Policy-makers’ perspective on ITS, ITS management,
Traveler Information Systems, Public transit, bicycles and
pedestrians, Eco-friendly and sustainable ITS solutions, ITS
technologies: Automated highway systems (AHS),
Autonomous Vehicles, Intelligent Infrastructures,
Evaluation of technologies and large-scale ITS field tests,
benefits and costs assessment of ITS, Learning from ITS
deployments in various countries, ITS Challenges and Issues:
Technical, institutional, funding, and procurement
issues, ITS evaluation software, Public and private sector
perspectives (institutional and stakeholder issues) on ITS.

41. AI 829 Social Simulations (3, 0)

Pre-requisite: None
Recommended Books:
Introduction to Computational Social Science: Principles and Applications
(2017), by Claudio Cioffi-Revilla, 2nd Ed. Springer
Simulation for the Social Scientist (2005), by Nigel Gilbert, Klaus Troitzsch,
2nd Edition, Open University Press
Monte Carlo Simulation and Resampling Methods for Social Science (2013), by
Thomas Carsey, First Edition, SAGE Publications
Interdisciplinary Applications of Agent-Based Social Simulation and Modeling
(2014), by Diana Francisca Adamatti, Graçaliz Pereira Dimuro, Helder Coelho,
1st Edition, IGI Global
Credit Hours: 3 (3, 0)
Course Objectives:
On completion of the course, the student should be able to answer:
• When agent-based models are most fruitfully applied,
• How to construct a conceptual agent-based model and then formalize it,
• How to implement the formalized model as custom computer software in
Netlogo,
• How to use the Netlogo programs to carry out simulation experiments
that will produce scientifically defensible assertions, and
• A broad range of applications of ABM in contemporary sociology
research.
Allocated
Topics / Contents
Periods
In this course we will learn how artificial societies can be
specified (agent-based modeling) and then made to exist and
evolve in time (computer simulation). The techniquesof 45
modeling and simulation provide a systematic way to state
and test hypotheses about the microscopic mechanisms (e.g.
individual behaviors) that might plausibly be responsible for
the emergence of observed macroscopic
systemic social patterns. Primary contents covered in the
course will constitute to answer (i) when agent-based models
are most fruitfully applied (ii) how to construct a conceptual
agent-based model and then formalize it, (iii) how to
implement the formalized model as custom computer
software in Netlogo, and (iv) how to use the Netlogo
programs to carry out simulation experiments that will
produce scientifically defensible assertions. To achieve all
this, the course will begin with a few "toy examples",and
then a series of research papers in sociology (and the social
sciences more broadly) in which agent-based modeling and
simulation has played a central role. For each of these papers,
the nature of the question would be dissected, the agent-
based model, the simulation, the experiments, and the
conclusions -- whenever possible, would be attempted to re-
create the results using hands-on (computer) laboratory
experiments. In the course students will gain an appreciation
for the importance of agent-based simulation in sociology
research, and begin to become empowered to create their
own models and apply simulation techniques towards
sociological research questions of interest to us. Agent-based
Modelling and Simulation in the Social and Human
Sciences (2007), by
Denis Phan, Frederic Amblard, The Bardwell Press

42. AI 838 Serious Games (3, 0)

Pre-requisite: None
Recommended Books:
Serious Games, Foundations, Concepts and Practice (2016), by Dörner, R.,Göbel,
S., Effelsberg, W., Wiemeyer, J., Springer
Serious Games: Mechanisms and Effects (2009), by Ute Ritterfeld, Michael J.
Cody, Peter Vorderer, Routledge Publications
The Art of Serious Game Design: A hands-on workshop for developing
educational games: Facilitator guide, by Digital Education Strategies, The Chang
School of Continuing Education, Ryerson University
Rules of Play: Game Design Fundamentals, Katie Salen, Eric Zimmerman
What Video Games Have to Teach Us About Learning and Literacy. Second
Edition, James Paul Gee Recent research:
Affective Ludology: Scientific Measurement of User Experience in Interactive
Entertainment, Ph.D. Thesis, Lennart E. Nacke (2009)
Credit Hours: 3 (3, 0)
Course Objectives:
On completion of the course, the student should be able to:
 • Critically appraise legal and ethical aspects of recording and storing
personal data gathered in conjunction with gaming activity
• Evaluate user interface design, and to conduct rigorous analysis of
human-computer interactions presented by such designs
• Evaluate and judge the effects of video games both in general and for
specialized domains
• Have an in-depth understanding of the psychophysiology and
psychometrics underlying serious game design
• Understand the range of game mechanics used in games to engage the
user
• Understand the effects of games on player behavior
• Identify and critically examine primary literature in the area of serious
games

Allocated
Topics / Contents
Periods
The field of modeling and simulation is large and diverse;
modeling and simulation is applied in every discipline to
answer questions in research and development and for 45
education and training. Recently there has been a push in the
use of specific simulations which have an internal goal. Such
simulations are known as games (when applied toeducation
and training, they are known as serious games) and provide
an experience that is fun and engaging making them
particularly relevant to the current generation of learners.
This course is an introduction to simulation with an emphasis
on serious games. Primary contents which would be covered
in this course will include, Ethical considerations of using
games to change behavior, Game interfaces, Universal
design, Research methodologies for game interactions,
Game telemetry, Game metrics, AI
evaluation techniques for "big data" from game telemetry,
Evaluation techniques for games research.

43. AI 856 Ethical Machines (3, 0)

Pre-requisite: None
Recommended Books:
Machine Ethics (2011), by Michael Anderson, Susan Leigh Anderson, 1st
Edition, Cambridge University Press
Machine Ethics and Robot Ethics (2016), by Wendell Wallach, Peter Asaro, 1st
Edition, CRC Press.
Moral Machines, Teaching Robots Right from Wrong (2010), by Wendell
Wallach, Colin Allen, Oxford University Press, 2009
The Technological Singularity (2015), by Murray Shanahan, MIT Press.
Weapons of Math Destruction: How Big Data Increases Inequality and
Threatens Democracy (2016), by Cathy O'Neil, Crown Publications
Moral Machines: Teaching Robots Right from Wrong (2010), by Wendell
Wallach, Colin Allen, 1st Edition, Oxford University Press.
Credit Hours: 3 (3, 0)
Course Objectives:
On completion of the course, the student should be able to:
• hone their skills in critically exploring the development and implications
of AI systems.
• have gained a broader conception of dilemmas in current AI technologies
• have a stronger framework with which to develop their own ethical
responsibilities.
Allocated
Topics / Contents
Periods
Recent advances in computing may place us at thethreshold
of a unique turning point in human history. Soon we are
likely to entrust management of our environment, economy, 45
security, infrastructure, food production, healthcare, and to a
large degree even our personal activities, to artificially
intelligent computer systems. The autonomous systems raise
many complex and troubling questions. How will society
respond as versatile robots and machine-learning systems
displace an ever-expanding spectrum of blue- and white-
collar workers? Will the benefits of this technological
revolution be broadly distributed or accrue to a lucky few?
How can we ensurethat these systems respect our ethical
principles when they make decisions at speeds and for
rationales that exceed our ability to comprehend? What, if
any, legal rights and responsibilities should we grant them?
And should we regard them merely as sophisticated tools or
as a newly emerging form of life? The goal this course is to
equip students with the intellectual tools, ethical foundation,
and psychological framework to successfully navigate the
coming age of intelligent machines. Primary contents ofthis
course will include, Overview of the history and issues raised
by Artificial Intelligence, Philosophical issues, Ethical
problems, Legal, social and economic impact, and
Future challenges.