Author pages are created from data sourced from our academic publisher partnerships and public sources.

- Publications
- Influence

An Autoencoder Approach to Learning Bilingual Word Representations

- A. Chandar, Stanislas Lauly, +4 authors Amrita Saha
- Computer Science, Mathematics
- NIPS
- 6 February 2014

Cross-language learning allows one to use training data from one language to build models for a different language. Many approaches to bilingual learning require that we have word-level alignment of… Expand

EPOpt: Learning Robust Neural Network Policies Using Model Ensembles

- A. Rajeswaran, Sarvjeet Ghotra, Sergey Levine, Balaraman Ravindran
- Computer Science, Mathematics
- ICLR
- 5 October 2016

Sample complexity and safety are major challenges when learning policies with reinforcement learning for real-world tasks, especially when the policies are represented using rich function… Expand

Correlational Neural Networks

- A. Chandar, Mitesh M. Khapra, H. Larochelle, Balaraman Ravindran
- Computer Science, Mathematics
- Neural Computation
- 27 April 2015

Common representation learning (CRL), wherein different descriptions (or views) of the data are embedded in a common subspace, has been receiving a lot of attention recently. Two popular paradigms… Expand

Diversity driven attention model for query-based abstractive summarization

- Preksha Nema, Mitesh M. Khapra, Anirban Laha, Balaraman Ravindran
- Computer Science
- ACL
- 26 April 2017

Abstractive summarization aims to generate a shorter version of the document covering all the salient points in a compact and coherent fashion. On the other hand, query-based summarization highlights… Expand

An algebraic approach to abstraction in reinforcement learning

- Balaraman Ravindran, A. Barto
- Mathematics
- 2004

To operate effectively in complex environments learning agents ignore irrelevant details. Stated in general terms this is a very difficult problem. Much of the work in this field is specialized to… Expand

- 81
- 11

Latent dirichlet allocation based multi-document summarization

- R. Arora, Balaraman Ravindran
- Computer Science
- AND '08
- 24 July 2008

Extraction based Multi-Document Summarization Algorithms consist of choosing sentences from the documents using some weighting mechanism and combining them into a summary. In this article we use… Expand

Accurate mobile robot localization in indoor environments using bluetooth

- A. N. Raghavan, Harini Ananthapadmanaban, Manimaran Sivasamy Sivamurugan, Balaraman Ravindran
- Computer Science, Engineering
- IEEE International Conference on Robotics and…
- 3 May 2010

In this paper, we describe an accurate method for localization of a mobile robot using bluetooth. We introduce novel approaches for obtaining distance estimates and trilateration that overcome the… Expand

Efficient Computation of the Shapley Value for Centrality in Networks

- Aadithya V. Karthik, Balaraman Ravindran, Tomasz P. Michalak, N. Jennings
- Computer Science
- WINE
- 13 December 2010

The Shapley Value is arguably the most important normative solution concept in coalitional games. One of its applications is in the domain of networks, where the Shapley Value is used to measure the… Expand

Efficient Computation of the Shapley Value for Game-Theoretic Network Centrality

- Tomasz P. Michalak, Aadithya V. Karthik, P. Szczepanski, Balaraman Ravindran, N. Jennings
- Computer Science
- J. Artif. Intell. Res.
- 3 February 2014

The Shapley value--probably the most important normative payoff division scheme in coalitional games--has recently been advocated as a useful measure of centrality in networks. However, although this… Expand

Model Minimization in Hierarchical Reinforcement Learning

- Balaraman Ravindran, A. Barto
- Computer Science
- SARA
- 2 August 2002

When applied to real world problems Markov Decision Processes (MDPs) often exhibit considerable implicit redundancy, especially when there are symmetries in the problem. In this article we present an… Expand