Artificial Intelligence

QUIC & DIRTY: A Quadratic Approximation Approach for Dirty Statistical Models NeurIPS 2014 RAAM: The Benefits of Robustness in Approximating Aggregated MDPs in Reinforcement Learning NeurIPS 2014 Random Bayesian networks with bounded indegree AISTATS 2014 Randomized Experimental Design for Causal Graph Discovery NeurIPS 2014 Realtime and Robust Hand Tracking from Depth CVPR 2014 Recognizing RGB Images by Learning from RGB-D Data CVPR 2014 Reconstructing Evolving Tree Structures in Time Lapse Sequences CVPR 2014 Recurrent Models of Visual Attention NeurIPS 2014 Recursive Inversion Models for Permutations NeurIPS 2014 Reducing Dueling Bandits to Cardinal Bandits ICML 2014 Reinforcement Learning for Closed-Loop Propofol Anesthesia: A Study in Human Volunteers JMLR 2014 Repeated Contextual Auctions with Strategic Buyers NeurIPS 2014 Restricted Boltzmann machines modeling human choice NeurIPS 2014 Revisiting Bayesian Blind Deconvolution JMLR 2014 Robot Programming by Demonstration with Interactive Action Visualizations RSS 2014 Robust and Agile 3D Biped Walking With Steering Capability Using a Footstep Predictive Approach RSS 2014 Robust Bayesian Max-Margin Clustering NeurIPS 2014 Robust learning of inhomogeneous PMMs AISTATS 2014 Robust Online Multi-Object Tracking based on Tracklet Confidence and Online Discriminative Appearance Learning CVPR 2014 Robust Policies via Meshing for Metastable Rough Terrain Walking RSS 2014 Robust Principal Component Analysis with Complex Noise ICML 2014 Robust RegBayes: Selectively Incorporating First-Order Logic Domain Knowledge into Bayesian Models ICML 2014 Sample Efficient Reinforcement Learning with Gaussian Processes ICML 2014 Sampling for Inference in Probabilistic Models with Fast Bayesian Quadrature NeurIPS 2014 Scalable 3D Tracking of Multiple Interacting Objects CVPR 2014