Professional Documents
Culture Documents
The main purpose of this course is to provide the most fundamental knowledge about Artificial Intelligence and
Machine Learning. It will provide understanding of the basic techniques for building intelligent computer systems
and an understanding of how AI is applied in problems.
Course Contents:
Module I: Introduction: (6 Hours)
Definitions of Artificial Intelligence, AI Problems, Production Systems, State Space Representation, Branches of
Artificial Intelligence, Applications of AI. Heuristic Search Techniques, Problem Reduction.
Components A CT S/V/Q/HA EE
Weightage (%) 5 15 10 70
CT: Class Test, HA: Home Assignment, S/V/Q: Seminar/Viva/Quiz, EE: End Semester Examination; A: Attendance
Course Outcomes:
Upon successful completion of this unit, students should be able to:
· Apply the concept of Linear algebra to the Artificial Intelligence.
· Understand the appropriateness of probability theory and need of fuzzy set theory for Artificial
Intelligence.
· Formulate scalable and accurate implementations of the most important optimization algorithms
for Artificial Intelligence.
· Characterize trade-offs between time, data and accuracy for optimization technique.
Examination Scheme:
Weightage (%) 5 15 10 70
A: Attendance, CT: Class Test,:, S/V/Q/HA: Seminar/Viva/Quiz/ Home Assignment, EE: End Semester
Examination;
Course Objective:
The course is designed to provide an in-depth appreciation of the central challenges in realizing aspects of human
cognition (with specific focus on language and memory) on machine. It surveys significant breakthroughs in our
understanding till date, and identifies avenues for exploration in future.
Course Contents:
Module I: Introduction: (6 Hours)
Declarative/ logic-based computational cognitive modeling, connectionist models of cognition, Bayesian models of
cognition, a dynamical systems approach to cognition.
Course Outcomes:
At the end of this course, students will demonstrate ability to:
· To apply concepts of classes and objects in real world scenarios.
· Understand Domains of cognitive psychology, Cognitive Neuroscience and Nervous system.
· Understand about Learning.
· Understand about Human intelligence which will include Measurement of intelligence, Artificial
Intelligence, Language, Structure of language, Comprehension of language.
· Learn about Cognitive process, Cognitive biases and Cognitive deficits.
Examination Scheme:
Components A CT S/V/Q/HA EE
Weightage (%) 5 15 10 70
Annexure 9
CT: Class Test, HA: Home Assignment, S/V/Q: Seminar/Viva/Quiz, EE: End Semester Examination; A: Attendance
Text & References:
Text:
Machine Learning. Tom Mitchell. First Edition, McGraw- Hill, 1997.
Introduction to Machine Learning Edition 2, by Ethem Alpaydin
References:
· The Cambridge Handbook of Computational Psychology, Ron Sun (ed.), Cambridge University Press
(2008)
· The Oxford Handbook of Computational and Mathematical Psychology, Jerome R. Busemeyer, Zheng
Wang, James T.
· Townsend, Ami Eidels (ed.), Oxford University Press (2015)
· Formal Approaches in Categorization, Emmanuel M. Pothos, Andy J. Wills, Cambridge University Press
(2011)
· Quantum Models of Cognition and Decision, Jerome R. Busemeyer, Peter D. Bruza, Cambridge
University Press (2014)
· The Quest for Artificial Intelligence, Nils J. Nilsson, Cambridge University Press (2009)
Annexure 9
Course Outcomes:
Learner will learn
· Advanced data analysis with R
· To build models with R
· To train and test data
Examination Scheme:
IA EE
5 10 15 35 15 10 10
Note: IA –Internal Assessment, EE- External Exam, A- Attendance PR- Performance, LR – Lab Record, V – Viva.
Course Outcomes:
At the end of this course, students will demonstrate ability to:
• Differentiate between supervised, unsupervised, semi-supervised machine learning approaches
• Discuss the decision tree algorithm and indentity and overcome the problem of overfitting
• Discuss and apply the back propagation algorithm and genetic algorithms to various problems
• Apply the Bayesian concepts to machine learning
• Analyse and suggest appropriate machine learning approaches for various types of problems
Examination Scheme:
Components A CT S/V/Q/HA EE
Weightage (%) 5 15 10 70
CT: Class Test, HA: Home Assignment, S/V/Q: Seminar/Viva/Quiz, EE: End Semester Examination; A: Attendance
References:
· Tom M. Mitchell, ―Machine Learning, McGraw-Hill Education (India) Private Limited, 2013.
· Ethem Alpaydin, ―Introduction to Machine Learning (Adaptive Computation and Machine Learning), The
MIT Press 2004.
· Stephen Marsland, ―Machine Learning: An Algorithmic Perspective, CRC Press, 2009.
Annexure 9
· Christopher M. Bishop, Pattern Recognition and Machine Learning.
MACHINE LEARNING TECHNIQUES LAB
List of experiments/demonstrations:
1 Python in Machine Learning
2 Data Preprocessing
3 Data Analysis
4 Summarizing the Dataset .
5 Training Data
6 Test Data
7 Performance Measures: Bias and Variance
8 PYTHON MACHINE LEARNING – TECHNIQUES. Classification, Regression, Clustering
9 PYTHON MACHINE LEARNING – ALGORITHMS
10 Traffic Congestion Analysis and Predictions
Course Outcomes:
Learner will learn
Understand the implementation procedures for the machine learning algorithms.
Design Java/Python programs for various Learning algorithms.
Apply appropriate data sets to the Machine Learning algorithms.
Identify and apply Machine Learning algorithms to solve real world problems.
Examination Scheme:
IA EE
5 10 15 35 15 10 10
Note: IA –Internal Assessment, EE- External Exam, A- Attendance PR- Performance, LR – Lab Record, V – Viva.
References:
· Tom M. Mitchell, ―Machine Learning, McGraw-Hill Education (India) Private Limited, 2013.
· Ethem Alpaydin, ―Introduction to Machine Learning (Adaptive Computation and Machine Learning),
The MIT Press 2004.
· Stephen Marsland, ―Machine Learning: An Algorithmic Perspective, CRC Press, 2009.
· Christopher M. Bishop, Pattern Recognition and Machine Learning.
Annexure 9
NEURAL NETWORKS AND DEEP LEARNING
Course Contents:
Module I: Introduction: (6 Hours)
Various paradigms of learning problems, Perspectives and Issues in deep learning framework, review of
fundamental learning techniques.
Course Outcomes:
At the end of this course, students will demonstrate ability to:
· Identify the deep learning algorithms which are more appropriate for various types of learning tasks in
various domains.
· Implement deep learning algorithms and solve real-world problems.
Examination Scheme:
Components A CT S/V/Q/HA EE
Weightage (%) 5 15 10 70
CT: Class Test, HA: Home Assignment, S/V/Q: Seminar/Viva/Quiz, EE: End Semester Examination; A: Attendance
Text:
· Machine Learning by Saikat Dutt , Subramanian Chandramouli, Pearson Education; First edition (1
October 2018)
· Goodfellow, I., Bengio,Y., and Courville, A., Deep Learning, MIT Press, 2016..
· Bishop, C. ,M., Pattern Recognition and Machine Learning, Springer, 2006.
References:
· Yegnanarayana, B., Artificial Neural Networks PHI Learning Pvt. Ltd, 2009.
· Golub, G.,H., and Van Loan,C.,F., Matrix Computations, JHU Press,2013.
· Satish Kumar, Neural Networks: A Classroom Approach, Tata McGraw-Hill Education, 2004.
Annexure 9
NEURAL NETWORKS AND DEEP LEARNING LAB
List of experiments/demonstrations:
· Introductory session on neural network tools
· Neural Network with Python
· Implementing, training, and evaluating neural networks
· Image Classification with Deep Convolutional Networks
· Feedforward Networks for Handwritten Digit Recognition
· Deep Feedforward Networks.
· Recurrent and Recursive Networks.
· Convolutional Networks.
· R Adversarial Learning.
Course Outcomes:
Learner will learn
· Identify the deep learning algorithms which are more appropriate for various types of learning tasks in
various domains.
· Implement deep learning algorithms and solve real-world problems.
Examination Scheme:
IA EE
5 10 15 35 15 10 10
Note: IA –Internal Assessment, EE- External Exam, A- Attendance PR- Performance, LR – Lab Record, V – Viva.
Course Contents:
Module I: Introduction: (6 Hours)
Robotics, Components of Robot,Robotic Paradigms, History of Robotics,Representative Architectures, Advantages
and Disadvantages
Course Outcomes:
At the end of this course, students will learn:
· Basic techniques in artificial intelligence, including probabilistic inference, planning and search algorithms,
localization, tracking, and PID control, all with a focus on robotics.
· To program all the major systems of a robotics.
Examination Scheme:
Components A CT S/V/Q/HA EE
Weightage (%) 5 15 10 70
CT: Class Test, HA: Home Assignment, S/V/Q: Seminar/Viva/Quiz, EE: End Semester Examination; A: Attendance
List of experiments/demonstrations:
1. Determination of maximum and minimum position of links.
2. Verification of transformation (Position and orientation) with respect to gripper and world coordinate
system
3. Estimation of accuracy, repeatability and resolution.
4. Robot programming and simulation for pick and place
5. Robot programming and simulation for Colour identification
6. Robot programming and simulation for Shape identification
7. Robot programming and simulation for machining (cutting, welding)
8. Robot programming and simulation for writing practice
9. Robot programming and simulation for any industrial process ( Packaging, Assembly)
10. Robot programming and simulation for multi process.
11. Modeling of problems related to kinematics and dynamics of robot using MATLAB
Course Outcomes:
Learner will learn
· Basics of matlab,
· Use of any robotic simulation software to model the different types of robots and calculate work volume for
different robots
Examination Scheme:
IA EE
5 10 15 35 15 10 10
Note: IA –Internal Assessment, EE- External Exam, A- Attendance PR- Performance, LR – Lab Record, V – Viva.