IISc offers a dedicated Masters Course in Artificial Intelligence. Click on the following Link for more information on the course Program Click Here
Background Courses
Several departments at IISc offer background courses that will help you build a strong foundation towards studying AI. If you are a PhD or Masters’ student interested in working in AI, it is extremely important that you build a strong background in the following subjects as soon as possible on joining IISc:
- E1 222: Stochastic Models and Applications OR E2 202: Random Processes
- E0 299: Computational Linear Algebra
- E0 230: Computational Methods of Optimization
- E1 213: Pattern Recognition and Neural Networks OR E0 270: Machine Learning
Introductory / Intermediate Courses
There are several introductory and intermediate level courses, offered both within CSA and in other departments, that will teach you the fundamental tools and techniques in machine learning and related fields:
- E1 277 Reinforcement Learning
- E1 216 Computer Vision
- E9 241: Digital Image Processing
- E9 261: Speech Information Processing
- E1 254: Game Theory
- E0 259 Data Analytics
- E2 231 Topics in Statistical Methods
- E9 206 Digital Video: Perception and Algorithms
Recommended Electives
- E0 265 Convex Optimization and Applications
- E0 334 Deep Learning for Natural Language Processing
- E0 268: Practical Data Science
- DS 256: Scalable Systems for Data Science
- E9 205 Machine Learning for Signal Processing
- DS 222: Machine Learning with Large Datasets
- DS 265: Deep Learning for Computer Vision
- E0 306 Deep Learning: Theory and Practice
- E0 249 Approximation Algorithms
- E0 235 Cryptography
- E0 238 Intelligent Agents
- E2 201: Information Theory
- E1 245: Online Prediction and Learning
- E2 336: Foundations of machine learning
- E2 207: Concentration Inequalities
- E1 244: Detection and Estimation Theory
- E1 396: Topics in Stochastic Approximation Algorithms
- E2 230: Network Science and Modelling
- E1 246: Natural Language Understanding
- E9 253: Neural Networks and Learning Systems
- CPS 313: Autonomous Navigation
Related Courses
Finally, a variety of more advanced courses are offered at various times that will help you connect the material learned in previous courses with topics of current research interest:
- E0 232: Probability and Statistics
- E0 219: Linear Algebra and Applications
- E0 225: Design and Analysis of Algorithms
- E0 268: Data Mining
- E0 233: Information Theory, Inference and Learning Algorithms
- E0 290: Mathematical Foundations for Modern Computing
- E0 370: Statistical Learning Theory
- E0 269: Probabilistic Graphical Models
- E0 371: Topics in Machine Learning
- E1 313: Topics in Pattern Recognition
- E1 395: Topics in Stochastic Control and Reinforcement Learning
- E0 352: Topics in System Research: Learning for Computer Systems
- E0 330: Convex Optimization
- E0 331: Optimization for Machine Learning
- SE305: Topics in Web-scale Knowledge Harvesting
- E0 238: Artificial Intelligence
- E0 202 Automated Software Engineering with Machine Learning
- E0 203 Spectral Algorithms
- E9 205: Machine Learning for Speech Processing
Courses on Other Topics
In addition to the courses listed above, there are a variety of other courses that you may wish to explore. For example, several of our students take courses in the Mathematics, EE, and ECE departments to further strengthen their mathematical and statistical backgrounds; in particular, if you are a PhD student working in machine learning or learning theory, you may find some of the following courses beneficial:
- MA 221: Analysis I
- MA 222: Analysis II
- MA 223: Functional Analysis
- MA 368: Topics in Probability and Stochastic Processes
- MA 369: Random Matrix Theory
- E2 212: Matrix Theory
Some students take courses in biology or in other fields in which they want to apply machine learning techniques. Within computer science, subjects such as algorithms, complexity, graph theory, and game theory all provide useful techniques and have fascinating interfaces with machine learning; subjects such as information retrieval, natural language processing, computer vision, communication networks, and computer systems all provide natural problems where machine learning techniques are applied. Finding new bridges between machine learning and other disciplines is up to your imagination!