21ME482 Introduction to AI and ML syllabus for ME

Introduction to AI:

Introduction, The Turing Test Approach, Cognitive Modeling Approach, Laws of thought Approach, Rational agent Approach, AI Methods and tools, Foundations of Artificial Intelligence, Goals of AI, Performing Natural Language Processing using Email Filters in Gmail, Performing Natural Language Generation using Smart replies in Gmail.

Fundamentals of Machine Learning:

Describing structural patterns, Machine Learning, Data Mining, Simple Examples, Fielded Examples, Machine Learning and statistics, Generalization as a search, Data mining and ethics.Data preprocessing using Weka, Handling high dimensional data through feature reduction in Weka.

Machine Learning Tasks:

Decision Tables, Decision Trees, Classification rules, Association rules, Rules with exceptions, Rules involving relations, Trees for numeric prediction, Instancebased representation, Clusters.Building soybean classification model using decision trees, generating association rules on weather data using Weka, Exploring Classification and Clustering techniques using scikit-learn or Weka.

Nature-inspired techniques in AI:

Inspiration from brain, Perceptron, Artificial Neural Net, Unsupervised Learning, Genetic Algorithms. Weather Prediction through Neural Networks using Weka, Perform data labelling for various images using Supervisely.

Deep Learning:

Basics of Deep Learning, Medical Image Analysis using Tensor Flow or Supervisely. Present and Future trends: The social effects of AI, A World with Robots, AI and Art, The Future, Integration, Artificial agents.

Course outcome (Course Skill Set)

At the end of the course the student will be able to:

• Understand the basic principles and goals of AI tasks.
• Outline the role of AI in different real-time applications.
• Construct a problem with the suitable AI task.
• Demonstrate the importance of biology in AI.
• Survey the future development of AI.

Assessment Details (both CIE and SEE)

• The weightage of Continuous Internal Evaluation (CIE) is 50% and for Semesteracademic End Exam (SEE) is 50%.
• The minimum passing mark for the CIE is 40% of the maximum marks (20 marks out of 50).
• A student shall be deemed to have satisfied the requirements and earned the credits allotted to each subject/ course if the student secures not less than 35% ( 18 Marks out of 50)in the semester-end examination(SEE), and a minimum of 40% (40 marks out of 100) in the sum total of the CIE (Continuous Internal Evaluation) and SEE (Semester End Examination) taken together Continuous internal Examination (CIE) Three Tests (preferably in MCQ pattern with 20 questions) each of 20 Marks (duration 01 hour)

7. First test at the end of 5th week of the semester

8. Second test at the end of the 10th week of the semester

9. Third test at the end of the 15th week of the semester

Two assignments each of 10 Marks

5. First assignment at the end of 4th week of the semester

6. Second assignment at the end of 9th week of the semester

Quiz/Group discussion/Seminar, any two of three suitably planned to attain the COs and POs for 20 Marks (duration 01 hours)

The sum of total marks of three tests, two assignments, and quiz /seminar/ group discussion will be out of 100 marks and shall be scaled down to 50 marks

Semester End Examinations (SEE)

• SEE paper shall be set for 50 questions, each of 01 mark.
• The pattern of the question paper is MCQ (multiple choice questions).
• The time allotted for SEE is 01 hour.
• The student has to secure minimum of 35% of the maximum marks meant for SEE.

Suggested Learning Resources:

Text Book:

1. BlayWhitby, Artificial Intelligence: A Beginners Guide, Second Edition, One World Publisher, 2008.

2. Ian H. Witten, Eibe Frank, Data Mining: Practical Machine Learning Tools and Techniques, Morgan Kaufman Publishers, 3rd Edition, 2011.

Reference Books:

1. AurélienGéron,Hands on Machine Learning with Scikit-Learn and TensorFlow [Concepts, Tools, and Techniques to Build Intelligent Systems], Published by O’Reilly Media,2017

2. Elaine Rich, Kevin Knight and Shivashankar B. Nair, Artificial Intelligence,TMH Education Pvt. Ltd., 2008.

3. Dan W. Patterson, Introduction to Artificial Intelligence and Expert Systems, Pearson.