Artificial Intelligence Group


The Artificial Intelligence Group at UCSD engages in a wide range of theoretical and experimental research. Areas of particular strength include machine learning, reasoning under uncertainty, and cognitive modeling. Within these areas, students and faculty also pursue real-world applications to problems in computer vision, speech and audio processing, data mining, bioinformatics, and computer security. The Artificial Intelligence Group is part of a larger campus-wide effort in Computational Statistics and Machine Learning (COSMAL). Interdisciplinary collaborations are strongly supported and encouraged.

Raef Bassily (ITA Data Science Fellow)

James Foulds (ITA Data Science Fellow)

Fragkiskos Malliaros (ITA Data Science Fellow)

(02/17) Kamalika Chaudhuri receives a Google Faculty Research Award. Congratulations, Kamalika!

(02/17) Mengting Wan receives the Microsoft Research Fellowship. Congratulations, Mengting!

(09/16) Fragkiskos Malliaros joins UCSD as an ITA-Data Science Fellow. Welcome, Fragkiskos!

(09/16) Julian McAuley and Yisong Yue are organizing the Southern California Machine Learning Symposium at Caltech on November 18.

(09/16) Angelique Taylor wins an NSF GRFP and a Google Anita Borg Award. Congratulations, Angelique!

(09/16) Laurel Riek and collaborators receive a 1M dollar grant from NSF to improve human robot interaction. Congratulations!

(09/16) New faculty Laurel Riek joins us. Welcome to UCSD, Laurel!

(08/16) New faculty Ndapa Nakashole will be joining us in Jan 2017. Welcome, Ndapa!

(08/16) Akshay Balasubramani defended his thesis, and will be joining Stanford University as a postdoctoral researcher. Congratulations, Akshay!

Event-specific image importance, Y. Wang, Z. Lin, X. Shen, R. Mech, G. Miller, and G. Cottrell , In Computer Vision and Pattern Recognition (CVPR), 2016.

A single model explains both visual and auditory precortical coding, H. Shan, M. Tong, and G. Cottrell , Arxiv. Preprint, 2016.

Modeling the Visual Word Form Area using a deep convolutional neural network, S. Wiraatmadja, and G. Cottrell , In Proceedings of the 38th Annual Conference of the Cognitive Science Society, 2016.

A deep Siamese neural network learns the human-perceived similarity structure of facial expressions without explicit categories , S. Rao, Y. Wang, and G. Cottrell, In Proceedings of the 38th Annual Conference of the Cognitive Science Society, 2016.

Modeling the contribution of central versus peripheral vision in scene, object, and face recognition, P. Wang and G. Cottrell , In Proceedings of the 38th Annual Conference of the Cognitive Science Society, 2016.

Are face and object recognition independent? A neurocomputational modeling exploration, P. Wang, I. Gauthier, G. Cottrell, In Journal of Cognitive Neuroscience, 28:(4):558–574. doi:10.1162/jocn_a_00919, 2016.

Movement Coordination in Human-Robot Teams: A Dynamical Systems Approach, T. Iqbal, S. Rack, and L. Riek , In IEEE Transactions on Robotics. vol. 32, no. 4, pp. 909-919, 2016.

Tempo Adaptation and Anticipation Methods for Human-Robot Teams, T. Iqbal, M. Moosaei and L. Riek, In Robotics, Science and Systems (RSS) 2016 Workshop on Planning for Human-Robot Interaction, 2016.

Robot Perception of Human Groups in the Real World: State of the Art , A. Taylor, and L. Riek , In Proceedings of the AAAI Fall Symposium on Artificial Intelligence in Human-Robot Interaction (AI-HRI), 2016.

Exploring Implicit Human Responses to Robot Mistakes in a Learning from Demonstration Task , C. Hayes, M. Moosaei, and L. Riek , In IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN 2016), pp. 1-6, 2016.

Modeling ambiguity, subjectivity, and diverging viewpoints in opinion question answering systems, M. Wang and J. McAuley, In Proceedings of the 16th International Conference on Data Mining (ICDM), 2016.

Learning compatibility across categories for heterogeneous item recommendation, R. He, C. Packer and J. McAuley, In Proceedings of the 16th International Conference on Data Mining (ICDM), 2016.

Fusing similarity models with Markov chains for sparse sequential recommendation, R. He and J. McAuley, In Proceedings of the 16th International Conference on Data Mining (ICDM), 2016.

Optimal Binary Classifier Aggregation for General Losses, A. Balsubramani and Y. Freund, In Proceedings of the 30th Annual Conference on Neural Information Processing Systems (NIPS), 2016.

Active Learning from Imperfect Labelers, S. Yan, K. Chaudhuri and T. Javidi, In Proceedings of the 30th Annual Conference on Neural Information Processing Systems (NIPS), 2016.

Vista: A visually, socially, and temporally-aware model for artistic recommendation, R. He, C. Fang, Z. Wang and J. McAuley, In Proceedings of the 10th Annual Conference on Recommendation Systems (RecSys), 2016.

Sparse hierarchical embeddings for visually-aware one-class collaborative filtering, R. He, C. Lin, J. Wang and J. McAuley, In Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI), 2016.

On the (in)effectiveness of mosaicing and blurring as tools for document redaction, S. Hill, Z. Zhou, L. Saul and H. Shacham, In Proceedings of the 16th Privacy Enhancing Technologies Symposium (PETS), 2016.

Pairwise matching through max-weight bipartite belief propagation, Z. Zhang, J. Shi, J. McAuley, W. Wei, Y. Zhang and A. van den Hengel, In Proceedings of the Annual Conference on Computer Vision and Pattern Recognition (CVPR), 2016.

On the Theory and Practice of Differentially Private Bayesian Learning, J. Foulds, J. Geumlek, M. Welling and K. Chaudhuri, In Proceedings of the 30th Annual Conference on Uncertainty in Artificial Intelligence (UAI), 2016.

The Extended Littlestone’s Dimension for Learning with Mistakes and Abstentions, C. Zhang and K. Chaudhuri, In Proceedings of the 29th Annual Conference on Learning Theory (COLT), 2016.

Interactive Bayesian hierarchical clustering, S. Vikram and S. Dasgupta, In Proceedings of the 33rd International Conference on Machine Learning (ICML), 2016.

A cost function for similarity-based hierarchical clustering, S. Dasgupta, In the 48th ACM Symposium on Theory of Computing (STOC), 2016.

Addressing complex and subjective product-related queries with customer reviews, J. McAuley and A. Yang, In Proceedings of the 25th International World Wide Web Conference (WWW), 2016.

Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering, R. He and J. McAuley, In Proceedings of the 25th International World Wide Web Conference (WWW), 2016.

VBPR: Visual bayesian personalized ranking from implicit feedback, R. He and J. McAuley, In Procedings of the 30th AAAI Conference (AAAI), 2016.

Learning visual clothing style with heterogeneous dyadic co-occurrences, A. Veit, B. Kovacs, S. Bell, J. McAuley, K. Bala and S. Belongie, In Proceedings of the International Conference on Computer Vision (ICCV), 2015.

Social Context Perception for Mobile Robots, A. Nigam, and L. Riek, In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2015.

A Method for Automatic Detection of Psychomotor Entrainment, T. Iqbal and L. Riek, In IEEE Transactions on Affective Computing, Vol. 7, Issue 1, pp. 1-15, 2015.

Detecting Social Context: A Method for Social Event Classification Using Naturalistic Multimodal Data, M.F O'Connor, and L. D. Riek , In Proceedings of the 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition, 2015.

Performing Facial Expression Synthesis on Robot Faces: A Real-time Software System, M. Moosaei, C.J. Hayes and L. Riek , In Proceedings of the 4th International AISB Symposium on New Frontiers in Human-Robot Interaction, AISB, 2015.

Deep Q-learning for active recognition of GERMS: Baseline performance on a standardized dataset for active learning, M. Malmir, K. Sikka, D. Forster, J. Movellan, and G. Cottrell , In Proceedings of the British Machine Vision Conference (BMVC), pages 161.1-161.11. BMVA Press.

Example selection for dictionary learning, T. Tsuchida and G. Cottrell , In Proceedings of the International Conference on Learning Representations (ICLR), 2015.

Modeling the object recognition pathway: A deep hierarchical model using Gnostic fields, P. Wang, G. Cottrell, and C. Kanan , In Proceedings of the 37th Annual Conference of the Cognitive Science Society, 2015.

Humans Have Idiosyncratic and Task-specific Scanpaths for Judging Faces, C. Kanan, D. Bseiso, N. Ray, J. Hsiao, and G. Cottrell, In Vision Research: 108:67-76, 2015.

Bikers are like tobacco shops, formal dressers are like suits: Recognizing Urban Tribes with Caffe, Y. Wang and G. Cottrell, In IEEE Winter Conference on Applications of Computer Vision (WACV), 2015.

Improving latent factor models via personalized feature projection for one-class recommendation, T. Zhao, J. McAuley, I. King, In Proceedings of the 24th ACM International Conference on Information and Knowledge Management (CIKM), 2015.

Scalable semi-supervised aggregation of classifiers , A. Balsubramani, and Y. Freund, In Proceedings of the 29th Annual Conference on Neural Information Processing Systems (NIPS), 2015.

Active Learning from Weak and Strong Labelers, C. Zhang and K. Chaudhuri, In Proceedings of the 29th Annual Conference on Neural Information Processing Systems (NIPS), 2015.

Convergence Rates of Active Learning for Maximum Likelihood Estimation, K. Chaudhuri, S. Kakade, P. Netrapalli and S. Saghavi, NIPS 2015.

Spectral Learning of Large Structured HMMs for Comparative Epigenomics, C. Zhang, J. Song, K. Chen and K. Chaudhuri, In Proceedings of the 29th Annual Conference on Neural Information Processing Systems (NIPS), 2015.

Crowd-sourcing Feature Discovery as Adaptively Chosen Comparisons, J. Zou, A. Kalai and K. Chaudhuri, In Proceedings of the 3rd AAAI Conference on Human Computation and Crowdsourcing (HCOMP), 2015.

Top-N recommendation with missing implicit feedback, D. Lim, J. McAuley and G. Lanckriet, In Proceedings of the 9th Annual Conference on Recommendation Systems (Recsys), 2015.

Image-based recommendations on styles and substitutes, J. McAuley, C. Targett, J. Shi, A. van den Hengel, In Proceedings of the 38th Annual ACM SIGIR Conference (SIGIR), 2015.

Who is .com? Learning to parse WHOIS records, S. Liu, I. Foster, S. Savage, G. M. Voelker, and L. K. Saul, In Proceedings of the ACM Internet Measurement Conference (IMC), 2015.

From .academy to .zone: an analysis of the new TLD land rush, T. Halvorson, M. F. Der, I. Foster, S. Savage, L. K. Saul, and G. M. Voelker, In Proceedings of the ACM Internet Measurement Conference (IMC), 2015.

Failure analysis and prediction for the CIPRES science gateway, K. Singh, S. Smallen, S. Tilak, and L. K. Saul, In Proceedings of the 10th Gateway Computing Environments Workshop (GCE), 2015.

Inferring networks of substitutable and complementary products, J. McAuley, R. Pandey, J. Leskovec, In Proceedings of the 21st ACM Conference on Knowledge Discovery and Data Mining (KDD), 2015.

Optimally combining classifiers using unlabeled data , A. Balsubramani and Y. Freund, In Proceedings of the 28th Annual Conference on Learning Theory (COLT), 2015.

Learning from Data with Heterogeneous Noise using SGD, S. Song, K. Chaudhuri and A. D. Sarwate, In Proceedings of the 18th Annual International Conference on AI and Statistics (AISTATS), 2015.

Randomized partition trees for nearest neighbor search, S. Dasgupta and K. Sinha, Algorithmica, 72(1): 237-263, 2015.

Combining Databases and Signal Processing in Plato, Y. Katsis, Y. Freund, and Y. Papakonstantinou, In Proceedings of the 7th Biennial Conference on Innovative Data Systems Research (CIDR), 2015.