My current research interests span the broader area of machine learning, ranging from Spatio-temporal Abstractions in Reinforcement Learning to social network analysis and Data/Text Mining. Much of the work in my group is directed toward understanding interactions and learning from them.

Several people have asked me what background is needed to start working in machine learning. Here is an attempt at building a list by our group. Wiki Page.

Reinforcement Learning

One of the main focus of research in our group is on building situated learning agents that can incrementally solve larger and larger problems using structures built from prior experience. We look at this both from a spatial and temporal perspective, with motivations drawn from cognitive theories of representation.

From a spatial, or a representation, perspective we want agents to be able to incorporate only those aspects of their enivornment that are crucial for the task at hand. We build on the notion of MDP homomorphisms proposed in my thesis and have explored various extensions to this basic framework [RB 2004, RBM 2007, NR 2007, NR 2008].

These architectures work with an already abstract representation of the world. Closer to the sensory level we are looking at the learning of visual routines that can tell an agent what aspects of its visual input to focus on. These visual routines then act as the feature extraction units that the higher levels in the architecture choose from. This work is part of a joint project with Profs. Jeremy Wyatt and Richard Dearden from University of Birmingham and Dr. Anurag Mittal and myself, from this Department, funded by the British Council under the UKIERI program.

From a temporal perspective we have addressed issues of representations and sub-tasks - the question of what is an adequate representation for the sub-task at hand [RB 2003b, RB 2003c, RBM 2007]. We are currently working on using cognitively motivated representation schemes for hierarchical task architectures. On the question of building temporal hierarchical architectures, we are exploring issues regarding incremental learning of the hierarchy, combining learning and planning; and looking at more cognitively motivated representations of tasks and sub-tasks.

We are also exploring the realizations of these algorithms on real-robot platforms. This requires us to address issues that are closer to the sensory and motor control level, including visual cognition, and other localization mechanisms [BRK 2009]. We are also looking at transfer of learning from one robot to another under several constrained settings as well as the problem of learning from instructions.

Text Mining

Our group has been looking at the marriage of both semantic and statistical approaches to text mining tasks. Much of the work in the group has been driven by specific problems. We have worked on the problem of text summarization [SRR2006a, 2008ARb, 2008ARa] categorization [SRR2008, SRR2006b], clustering [JDR2008, JDRS2007], etc. Some of the current projects are focused on (auto | financial | micro) blog analysis (part of the work is funded by General Motors, India Science Labs), resume processing (funded by Burning Glass Technologies), representative document set mining, question answering systems, etc.

Data Mining

My interest in data mining has been motivated partly by my desire to understand the use of statistical models in mining, partly by my drive for doing something of immediate relevance, and partly by the connections between my work on abstraction and some of the problems in mining. One of the ongoing projects is on opthalmic data mining with Sankara Nethralaya^ [RKR2008, CR2008]. We work closely with doctors from their Vision Research Foundation on building better screening tools, disease incidence prediction, risk factor analysis, etc.

We are also looking at telecom data analysis, funded by Ericsson R & D, India. The problems we focus on is trying to understand customer behavior better through various analytics tools, including social network analysis [KR2009, AR2010].


These are wonderful people from outside IIT Madras that I am collaboarting with currently or have done so in the recent past, and hope to continue working with in the future.

  • Andrew G. Barto, University of Massachusetts, Amherst
  • Dipti Deodhare, Center for Artificial Intelligence and Robotics
  • K. Madhava Krishna, IIIT Hyderabad
  • Suril Shah, IIT Jodhpur
  • Sriraam Natarajan, Indiana University, Bloomington, USA
  • Jeremy Wyatt, University of Birmingham, UK
  • Srinivasan Parthasarathy, Ohio State, USA
  • Ramasuri Narayanam, IBM Research, Bengaluru
  • Anand Raghunathan, Purdue University, USA

Awards and Service

  • Won a UKIERI funded project in 2009, jointly with Jeremey Wyatt, Richard Dearden from University of Birmingham and Anurag Mittal, IIT Madras
  • KLA Tencor Facutly Research Engagement Grant, 2014, 2015, 2017
  • Yahoo! Faculty Research and Engagement Gift, 2009, 2014
  • Rachit Arora, best student paper award, AND 2008
  • Sanjukta Roy (CMI), best student paper award, CoDS 2015

  • Vice-President, India chapter of ACM SIGKDD, 2016-2018.
  • Secretary, India chapter of ACM SIGKDD, 2012-2015.
  • Member, ASSOCHAM committee on IT and ITES, 2016-2017.

  • Member, SEBI Committee of Financial and Regulatory Technology (CFRT), 2017-
  • Member, Research Evaluation Committee, India International Institute of Democracy and Election Management, Election Commission of India, 2017-

  • Member, Research Advisory Council, IIIT Sri City, 2017-
  • Member, Board of Studies, Thiagarajar College of Engineering, Madurai
  • Member, Board of Studies, SJCE, Mysore
  • Member, Board of Studies, Sri Chandrasekharendra Saraswathi Viswa Mahavidyalaya, Kanjeepuram
  • Member, Board of Studies, Sastra University, Tanjore
  • Member, Board of Studies, Central University of Tamil Nadu, Thiruvarur

  • General Co-Chair: IKDD CoDS 2017, IIT Madras, 9-11 March, 2017.
  • Program Co-Chair: PAKDD 2010, ADCOM 2013,2016, IKDD CODS 2014, COMAD 2016.
  • General Co-chair of 2015 Big Data Summit co-located with KDD 2015, Sydney Australia.
  • Co-organizer: CoLISD Workshop, with ECML PKDD 2011 (Athens), 2012 (Bristol).
  • Co-organizer of IMI Workshop on Social Networks, Chennai, February 2012.
  • Co-organzier of IMPECS workshop on Online Social Networks, Kharghpur, August 2012.
  • Co-organizer of Mysore Park workshop on Understanding Big Data Analytics, Mysore, February 2013.
  • Co-organizer of NetSci Workshop on Networks over Time, Copenhagen, Denmark, June, 2013.
  • Co-organizer of NMI-IITM Workshop on Recent Advances in Reinforcement Learning, Chennai, March 2015.
  • Co-organizer of Data Science in India Forum as part of the Big Data Summit 2016, colocated with KDD 2015, Sydney, Australia.
  • Co-organizer of Social Networking Workshop, part of COMSNETS, 2016, Bengaluru.
  • Co-organizer of Indo-German Spring School on Algorithms for Big Data, IIT Madras, 20-26 February, 2016.
  • Co-organizer of IJCAI Workshop on Deep Reinforcement Learning: Frontiers and Challenges, New York City, July 11, 2016.
  • Co-organizer of Data Science in India networking session during KDD 2016, San Fransico, USA.
  • Co-organizer of ICML 2017 Workshop on Lifelong Learning: A Reiforcement Learning Approach, Sydney, Australia, August 10, 2017.
  • Co-organizer of ICML 2017 Workshop on Reinforcement Learning, Sydney, August, 11, 2017.
  • Co-organizer of Data Science in India networking session during KDD 2017, Halifax, Canada, August 15, 2017.
  • Local Arrangmenets Chair: HOIT 2007.
  • Finance Chair: CoDS 2014, 2015.
  • Sponsorship Chair: CoDS-COMAD 2018.
  • Machine Learning Track Chair: ICISIP 2005.
  • Senior Program Committee Member: SDM 2015, IJCAI 2015, 2016, KDD 2016.
  • Program Committee Member: ICML 2008, 2015, 2017 AAAI 2010, 2012, 2014, 2015, 2016, 2017, 2018 AAMAS 2008, DASFAA 2007, 2008, AND 2008, 2009, 2010, 2011, 2012, IEEE CASE 2009, 2010, COMAD 2010, 2011, 2012, BASNA 2010, FLAIRS 2011, 2012, ECML PKDD 2012, 2013, NIPS 2012, 2013, 2014, 2015, 2016, 2017, CIKM 2012, 2013, ICDM 2012, 2014, RSS 2013, IJCAI 2013, 2017, ACML 2013, WWW 2014, 2017 ECML PKDD Nectar track 2015, 2016, SDM 2017, KDD 2017, RLDM 2013, 2015, 2017, CoRL 2017, ICAPS 2018.
  • Associate Editor: Sadhana, The Engineering Proceedings of the Indian Academy of Sciences, Springer.
  • Reviewer:
    ACM Transactions on Knowledge Discovery in Data
    IEEE Transactions on Systems, Man and Cybernetics A, B, and C
    IEEE Transactions on Circuits and Systems
    IEEE Transactions on Multimedia
    Information Processing and Management (Springer)
    Journal of Machine Learning Research
    Journal of Artificial Intelligence Research
    Journal of Algorithms (Elsivier)
    Proceedings of the Indian Academy of Sciences
    Robotics and Autonomous Systems (Springer)
    Wireless Networks (Springer)
    ICML 2002, 2003, ICRA 2012, 2014 and several other conferences