Fall 2019
This course gives a broad introduction to Artificial Intelligence and Machine Learning.
Clint P. George — clint [at] iitgoa [dot] ac [dot] in — Office: F9, New Academic Block A
Artificial Intelligence 3e: A Modern Approach (AIMA) by Russel and Norvig (2015)
Machine Learning by Mitchell (2009)
Pattern Recognition and Machine Learning (Information Science and Statistics) by Bishop (2010)
This is a core course designed for the fifth semester Computer Science and Engineering undergraduate students. Knowledge in computer programming is required.
Course prerequisites: CS 113, MA106, CS215, CS218, MA214
CS344: Quiz 1 (10%) — Midterm (25%) — Quiz 2 (10%) — Seminar (10%) — Final (35%) — Class Participation (10%)
CS386: 3-4 lab assignments/projects (60%) — Term Project (30%) — Class Participation (10%)
We expect that every student follows the highest standards of integrity and academic honesty. Copying/sharing code in exams, homeworks, lab sessions are not permitted. See the IIT Goa policy for academic malpractices.
Note: This is a tentative course schedule. It will be updated often. Also, log on to Classroom to see lecture slides, additional course materials, and announcements.
| S/N | Topic | Resources |
|---|---|---|
| 1 | k-Nearest Neigbhor (k-NN) Classifiers | kNN |
| 2 | Course Introduction and What's Artificial Intelligence? Reading: AIMA Sections 1.1 - 1.4 | |
| 3 | Problem solving agents and introduction to search problems | |
| 4 | Python tutorial | e.g. Python for Data Science, Introduction to Python |
| 5 | Uniformed Search : breadth-first search, depth-first search, and uniform-cost search Reading: AIMA Sections 3.1 - 3.2, breadth-first search, depth-first search | |
| 6 | Informed Search: heuristics, greedy search | |
| 7 | A* search | |
| 8 | A* search: properties, examples; Graph Search algorithms | |
| 9 | Interpreting Line Drawings | |
| 10 | Constraint satisfaction problems, backtracking | |
| 11 | Constraint satisfaction problems: variable and value ordering, filtering | |
| 12 | Constraint satisfaction problems: filtering, problem structure | |
| 13 | Constraint satisfaction problems: improving problem structure; Local search: hill climbing, simulated annealing Reading: genetic algorithms | |
| 14 | k-means clustering | |
| 15 | Topics in clustering: partition-based and bottom-up approaches | |
| 16 | The Perceptron learning algorithm | |
| 17 | Limiations of the Perceptron learning: improvements, the notion of the margin, overfitting, large margin classifiers | |
| 18 | Probability: review | |
| 19 | Probability: The Product rule, the Chain rule, Bayes' rule | Bayesian Thinking Bayes' rule - an intuitive explanation |
| 20 | Introduction to Artificial Neural Networks by A. Gupta | |
| 21 | Markov Models | |
| 22 | Bayes' net: representation | |
| 23 | Bayes' net: independence | |
| 24 | Bayes' net: independence | |
| 25 | Bayes' net: inference | |
| 26 | Bayes' net: inference |
| S/N | Date | Title | Resources |
|---|---|---|---|
| 1 | October 24 | Adversarial Search in Context Game: Mini-Max Search by Neeraj Khatri, Ujjawal Tiwari, Raj Jagtap | abstract, slides |
| 2 | October 22 | Improving local search: tabu search vs simulated annealing by Pallav Mathur, Dushyant Chetiwal, Tejas Mayekar | abstract, slides |
| 3 | October 29 | Google PageRank Algorithm and it’s Modification by Raj Hansini Khoiwal, Pulaksh Garg, Chetan Rajput | abstract, slides |
| 4 | October 16 | Adversarial search in the context of a game: Alpha-Beta pruning by Bhavam Gupta, Naresh Kumar Kaushal, Rajat Kumar Dalai | abstract, slides |
| 5 | October 22 | Ensemble Learning - Bagging and Random Forest by Rahul Kashyap, Muskan Jain, Priyanshu Singh | abstract, slides |
| 6 | October 23 | Ensemble Learning: Boosting by Vishrut Maheshwari, Harsh Dubey, Mehul Saxena | abstract, slides |
| 7 | October 16 | Decision Trees for Regression by Abhinav Kumar, Paras Yadav, Rahul Salunke | abstract, slides |
| 8 | October 30 | Interpretation of Line Diagrams and Waltz Algorithm by Advaith Alenkrith, V. Prakhyath Sree Harsha, Maganuru Jayasurya | abstract, slides |
| 9 | October 30 | Expectimax Search by Abhay Sharma, Rahul Ratneshwar Mandal, Gorthi Jaswanth | abstract, slides |
| 10 | October 21 | Genetic Algorithms by Deepak Das, Anshul Sharma, Nabh Spandan | abstract, slides |
| 11 | October 23 | Decision Tree for Classification by Kalyani Goyal, Rahul Bhaviskar, Ajay Meena | abstract, slides |
| S/N | Date | Title | Resources |
|---|---|---|---|
| 1 | November 28 | Retina Damage Detection for Diabetic Patients by Raj Jagtap, Neeraj Khatri, Ujjawal Tiwari, Raj Hansini Khoiwal, Pulaksh Garg | poster |
| 2 | November 28 | Forgery Detection by Advaith Alenkrith, Gorthi Jaswanth, V. Prakhyath Sree Harsha, Maganuru Jayasurya | poster |
| 3 | November 28 | Face Detection by Naresh Kumar Kaushal, Rajat Kumar Dalai, Bhavam Gupta, Priyanshu Singh | poster |
| 4 | November 28 | Emotion Recognition using Speech Analysis by Muskan Jain, Rahul Kashyap, Kalyani Goyal, Rahul Baviskar | poster |
| 5 | November 28 | Sentiment Analysis by Vishrut Maheshwari, Harsh Dubey, Chetan Rajput, Rahul Salunke | poster |
| 6 | November 28 | Detection of Pneumonia from Chest X-Ray Images using Deep CNN by Abhinav Kumar, Paras Yadav, Mehul Saxena, Rahul Ratneshwar Mandal | poster |
| 7 | November 28 | Stock Market Predictor by Deepak Das, Anshul Sharma, Nabh spandan, Abhay Sharma | poster |
| 8 | November 28 | Image to text conversion by Ajay Meena, Tejas Mayekar, Pallav Mathur, Dushyant Chetiwal | poster |