PPT-Efficient Large-Scale Structured Learning

Steve Branson Oscar Beijbom Serge Belongie CVPR 2013 Portland Oregon UC San Diego UC San Diego Caltech Overview Structured prediction Learning from larger datasets. Michal Per. ďoch. Ondřej Chum and Jiří Matas. Large Scale Object Retrieval. Large (web) scale “real-time” search involves millions(billions) of images. Indexing structure should fit into RAM, failing to do so results in a order of magnitude increase in response time. By. Chi . Bemieh. . Fule. August 6, 2013. THESIS PRESENTATION . Outline. . of. . today’s. presentation. Justification of the study. Problem . statement. Hypotheses. Conceptual. . framework. Research . Final Defense Presentation. by Steven Y. Ko. Thesis Focus. One class of operations. that faces . one common set of challenges. . cutting across . four diverse and popular types of distributed infrastructures. Sanjeev. . Arora. , . Rong. . Ge. Princeton University. Learning Parities with Noise. Secret u = (1,0,1,1,1). u ∙ (0,1,0,1,1) = 0. u ∙ (1,1,1,0,1) = 1. u ∙ (0,1,1,1,0) = . 1. Learning Parities with Noise. Introductions . Name. Department/Program. If research, what are you working on.. Your favorite fruit.. How do you estimate P(. y|x. ) . Types of Learning. Supervised Learning. Unsupervised Learning. Semi-supervised Learning. Jimmy Lin and Alek . Kolcz. Twitter, Inc.. Presented by: Yishuang Geng and Kexin Liu. 2. Outline. •Is twitter big data? . •How . can machine learning help twitter?. •Existing challenges?. •Existing literature of large-scale learning. Machine Learning. Large scale machine learning. Machine learning and data. Classify between confusable words.. E.g., {to, two, too}, {then, than}.. For breakfast I ate _____ eggs.. “It’s not who has the best algorithm that wins. . Outline. Some Sample NLP Task . [Noah Smith]. Structured Prediction For NLP. Structured Prediction Methods. Conditional Random Fields. Structured . Perceptron. Discussion. Motivating Structured-Output Prediction for NLP. via Brain simulations . Andrew . Ng. Stanford University. Adam Coates Quoc Le Honglak Lee Andrew Saxe Andrew Maas Chris Manning Jiquan Ngiam Richard Socher Will Zou . Thanks to:. Steve Branson . Oscar . Beijbom. . Serge . Belongie. CVPR 2013, Portland, Oregon. . UC San Diego. . UC San Diego. . Caltech. Overview. Structured prediction . Learning from larger datasets. Sanjeev. . Arora. , . Rong. . Ge. Princeton University. Learning Parities with Noise. Secret u = (1,0,1,1,1). u ∙ (0,1,0,1,1) = 0. u ∙ (1,1,1,0,1) = 1. u ∙ (0,1,1,1,0) = . 1. Learning Parities with Noise. Slides on LRTDP and UCT are courtesy . Mausam. /. Kolobov. . Ideas for Efficient Algorithms... Use heuristic search (and reachability information). LAO*, RTDP. Use execution and/or Simulation. “Actual Execution” Reinforcement learning. James E. Smith . 2014 ACM/IEEE 41st International Symposium on Computer Architecture (ISCA). 1. Presented by Rasmus Lüscher. Executive Summary. Motivation:. Large scale architectures are needed to emulate the neocortex to support research studying the operation of the brain.. Institute of High Energy Physics, CAS. Wang Lu (Lu.Wang@ihep.ac.cn). Agenda. Introduction. Challenges and requirements of anomaly detection in large scale storage systems . Definition and category of anomaly.