The curriculum of the two-year M.Tech. (AI) programme comprises a total of 64 credits of which 43 credits account for course-work and 21 credits for project work. The course-work is organized as follows:
- Pool-A courses (Hardcore): 19 credits
- Pool-B courses (Softcore): Minimum 12 credits
- Pool-C courses (Electives): Minimum credits to make a total of 43 credits of course-work
Pool-A courses
| E0 251 | 3:1 | Data Structures and Algorithms |
| E1 222 | 3:0 | Stochastic Models and Applications |
| (or) | ||
| E2 202 | 3:0 | Random Processes |
| E0 298 | 3:1 | Linear Algebra and Its Applications |
| E0 230 | 3:1 | Computational Methods of Optimization |
| E1 213 | 3:1 | Pattern Recognition and Neural Networks |
| (or) | ||
| E0 270 | 3:1 | Machine Learning |
| (or) | ||
| E2 236 | 3:1 | Foundations of Machine Learning |
Pool-B courses
| E1 277 | 3:1 | Reinforcement Learning |
| E1 216 | 3:1 | Computer Vision |
| E9 241 | 2:1 | Digital Image Processing |
| E9 261 | 3:1 | Speech Information Processing |
| E1 254 | 3:1 | Game Theory |
| E1 241 | 3:0 | Dynamics of Linear Systems |
| E0 259 | 3:1 | Data Analytics |
| E2 231 | 3:0 | Topics in Statistical Methods |
| E9 208 | 3:1 | Digital Video: Perception and Algorithms |
Project
| AI 299 | 0:21 | Dissertation Project |
Recommended Electives The recommended electives are listed below. Pool B courses could also be taken as electives. Courses not listed here could also be taken as electives with prior approval of the faculty advisor.
| E0 265 | 3:1 | Convex Optimization and Applications |
| E0 334 | 3:1 | Deep Learning for Natural Language Processing |
| E0 268 | 3:1 | Practical Data Science |
| DS 256 | 3:1 | Scalable Systems for Data Science |
| E9 205 | 3:1 | Machine Learning for Signal Processing |
| DS 222 | 3:1 | Machine Learning with Large Data sets |
| DS 265 | 3:1 | Deep Learning for Computer Vision |
| E0 306 | 3:1 | Deep Learning: Theory and Practice |
| E0 249 | 3:1 | Approximation Algorithms |
| E0 235 | 3:1 | Cryptography |
| E0 238 | 3:1 | Intelligent Agents |
| E2 201 | 3:0 | Information Theory |
| E1 245 | 3:0 | Online Prediction and Learning |
| E2 207 | 3:0 | Concentration Inequalities |
| E1 244 | 3:0 | Detection and Estimation Theory |
| E1 396 | 3:0 | Topics in Stochastic Approximation Algorithms |
| E2 230 | 3:0 | Network Science and Modelling |
| E1 246 | 3:1 | Natural Language Understanding |
| E9 253 | 3:0 | Neural Networks and Learning Systems |
| E9 309 | 3:1 | Advanced Deep Learning |
| CPS 313 | 2:1 | Autonomous Navigation |
Note: Students are advised to pay attention to the designation of a course at the time of registration on SAP. For example, a course designated as a Pool-C course at the time of registration cannot be redesignated as a Pool-B course later on. Also, the course type can be changed only from RTP to non-RTP and from credit to audit, and not the other way round.
(Last updated: February 28, 2022)