Deep Learning
Large Neural Networks with many layers have proven generally effective at a broad range of tasks and pose a unique set of challenges during learning and inference. We are investigating the properties and applications of such large Neural Nets.
Matthew Hausknecht Formerly affiliated Collaborator mhauskn [at] cs utexas edu
Karl Pichotta Ph.D. Student pichotta [at] cs utexas edu
Stephen Roller Ph.D. Student roller [at] cs utexas edu
Wesley Tansey Formerly affiliated Collaborator tansey [at] cs utexas edu
Subhashini Venugopalan Ph.D. Student vsub [at] cs utexas edu
     [Expand to show all 17][Minimize]
Captioning Images with Diverse Objects 2017
Subhashini Venugopalan, Lisa Anne Hendricks, Marcus Rohrbach, Raymond Mooney, Trevor Darrell, and Kate Saenko, To Appear In Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR-17) 2017.
Deep Compositional Captioning: Describing Novel Object Categories without Paired Training Data 2016
Lisa Anne Hendricks, Subhashini Venugopalan, Marcus Rohrbach, Raymond Mooney, Kate Saenko, and Trevor Darrell, In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR-16), pp. 1--10 2016.
Deep Imitation Learning for Parameterized Action Spaces 2016
Matthew Hausknecht, Yilun Chen, and Peter Stone, In AAMAS Adaptive Learning Agents (ALA) Workshop, Singapore, May 2016.
Deep Reinforcement Learning in Parameterized Action Space 2016
Matthew Hausknecht and Peter Stone, In Proceedings of the International Conference on Learning Representations (ICLR), San Juan, Puerto Rico, May 2016.
Improving LSTM-based Video Description with Linguistic Knowledge Mined from Text 2016
Subhashini Venugopalan, Lisa Anne Hendricks, Raymond Mooney, and Kate Saenko, In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP-16), pp. 1961--1966, Austin, Texas 2016.
Learning Statistical Scripts with LSTM Recurrent Neural Networks 2016
Karl Pichotta and Raymond J. Mooney, In Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI-16), Phoenix, Arizona, February 2016.
MGNC-CNN: A Simple Approach to Exploiting Multiple Word Embeddings for Sentence Classification 2016
Ye Zhang, Stephen Roller, and Byron Wallace., In Proceedings of the 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-16), pp. 1522--1527, San Diego, California 2016.
On-Policy vs. Off-Policy Updates for Deep Reinforcement Learning 2016
Matthew Hausknecht and Peter Stone, In Deep Reinforcement Learning: Frontiers and Challenges, IJCAI Workshop, New York, July 2016.
PIC a Different Word: A Simple Model for Lexical Substitution in Context 2016
Stephen Roller and Katrin Erk, In Proceedings of the 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-16), pp. 1121-1126, San Diego, California 2016.
Stacking With Auxiliary Features: Improved Ensembling for Natural Language and Vision 2016
Nazneen Fatema Rajani, PhD proposal, Department of Computer Science, The University of Texas at Austin.
Statistical Script Learning with Recurrent Neural Networks 2016
Karl Pichotta and Raymond J. Mooney, In Proceedings of the Workshop on Uphill Battles in Language Processing (UBLP) at EMNLP 2016, Austin, TX, November 2016.
Using Sentence-Level LSTM Language Models for Script Inference 2016
Karl Pichotta and Raymond J. Mooney, In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL-16), pp. 279--289, Berlin, Germany 2016.
Deep Recurrent Q-Learning for Partially Observable MDPs 2015
Matthew Hausknecht and Peter Stone, In AAAI Fall Symposium on Sequential Decision Making for Intelligent Agents (AAAI-SDMIA15), Arlington, Virginia, USA, November 2015.
Natural Language Video Description using Deep Recurrent Neural Networks 2015
Subhashini Venugopalan, PhD proposal, Department of Computer Science, The University of Texas at Austin.
Sequence to Sequence -- Video to Text 2015
Subhashini Venugopalan, Marcus Rohrbach, Jeff Donahue, Raymond J. Mooney, Trevor Darrell, and Kate Saenko, In Proceedings of the 2015 International Conference on Computer Vision (ICCV-15), Santiago, Chile, December 2015.
Statistical Script Learning with Recurrent Neural Nets 2015
Karl Pichotta, PhD proposal, Department of Computer Science, The University of Texas at Austin.
Translating Videos to Natural Language Using Deep Recurrent Neural Networks 2015
Subhashini Venugopalan, Huijuan Xu, Jeff Donahue, Marcus Rohrbach, Raymond Mooney, and Kate Saenko, In Proceedings the 2015 Conference of the North American Chapter of the Association for Computational Linguistics -- Human Language Technologies (NAACL HLT 2015), pp. 1494--1504, Denver, Colora...