Students have to finish a total of 12 credits, with at least one course from each of the following categories (rows). If a student has already completed some of these categories as part of the regular B.Tech Program, the student should take an equivalent number of elective credits to compensate.
| Courses | Category |
|---|---|
| AI2000 (or) AI5000 (or) CS5590 (or) CS3390 (or) EE2802 | Foundations of Machine Learning |
| AI2100 (or) AI5100 | Deep Learning |
| AI3001 | Advanced Topics in ML |
| List below | Electives |
Electives not in the given basket lists can be considered in a given basket with approval of faculty advisor (e.g. a new AI elective offered by a new faculty)
| AI and ML: Theory |
|---|
| Probabilistic Graphical Models |
| Statistical Learning Theory |
| Kernel Methods |
| Optimization Methods in Machine Learning |
| Convex Optimization |
| Reinforcement Learning |
| Artificial Intelligence |
| Bayesian Data Analysis |
| Representation Learning |
| Applied AI and ML |
|---|
| Computer Vision |
| Natural Language Processing |
| Speech Systems |
| Image and Video Processing |
| Data Analytics/Big Data |
| Applications of AI in Healthcare |
| Hardware Architectures for Machine Learning |
| Data Mining |
| Information Retrieval |
| AI for Humanity |
| Robotics |