Recent Changes

Sunday, January 1

  1. page Keynotes edited ... New York University http://yann.lecun.com ... Feature Hierarchies Slides Abstract: Int…
    ...
    New York University
    http://yann.lecun.com
    ...
    Feature Hierarchies Slides
    Abstract:
    Intelligent perceptual tasks such as vision and audition require the construction of good internal representations. Machine Learning has been very successful for producing classifiers, but the next big challenge for ML is to devise learning algorithms that can learn features and internal representations automatically.
    (view changes)
    8:21 pm
  2. page Tutorials edited ... National University of Singapore http://www.comp.nus.edu.sg/~leews ... Decision Process S…
    ...
    National University of Singapore
    http://www.comp.nus.edu.sg/~leews
    ...
    Decision Process Slides
    Abstract:
    Partially Observable Markov Decision Process (POMDP) provides a mathematically elegant formulation for adapting the actions of an agent based on past observations in order to achieve high expected rewards in the future. However, solving POMDPs is computationally intractable in the worst case, and until recently POMDPs were considered to be impractical for applications. In the last few years, tremendous progress has been made in solving POMDPs and they have been shown to be effective in application domains such as dialog systems, assistive technologies for the elderly, and aircraft collision avoidance systems. In this tutorial, we will go through the basic properties of POMDPs, try to understand when they are likely to be effectively solvable, and describe techniques for scaling to problems with very large state spaces and long search horizons.
    (view changes)
    8:08 pm
  3. file Lee_POMDP.pdf uploaded
    8:08 pm

Monday, December 26

  1. page Tutorials edited ... National Institute of Advanced Industrial Science and Technology http://www.cbrc.jp/~tsuda …
    ...
    National Institute of Advanced Industrial Science and Technology
    http://www.cbrc.jp/~tsuda
    ...
    Recent Developments Slides
    Abstract:
    Labeled Graphs are general and powerful data structures that can be used to represent diverse kinds of objects such as XMLs, chemical compounds, proteins, and RNAs. In these 10 years, we saw significant progress in statistical learning algorithms for graph data, such as supervised classification, clustering and dimensionality reduction.
    (view changes)
    11:52 pm
  2. file koji tsuda.pdf uploaded
    11:50 pm
  3. page Keynotes edited ... Department of Computer Science University of Bristol http://www.cs.bris.ac.uk/~flach/ ... …
    ...
    Department of Computer Science University of Bristol
    http://www.cs.bris.ac.uk/~flach/
    ...
    machine learning Slides
    Abstract:
    Calibration is the process of adjusting measurements to a standard scale. In machine learning it is most commonly understood in relation to the class probability estimates of a probabilistic classifier: we say that a classifier is well-calibrated if among all instances receiving a probability estimate p for a particular class, the proportion of instances having the class in question is approximately p. The advantage of a well-calibrated classifier is that near-optimal decision thresholds can be directly derived from the operating condition (class and cost distribution). In this talk I explore various methods for classifier calibration, including the isotonic regression method that relates to ROC analysis. I will discuss how these methods can be applied to single features, resulting in a very general framework in which features carry class information and categorical features can be turned into real-valued ones and vice versa. I will also discuss an alternative notion of calibration whereby a classifier's score quantifies the proportion of positive predictions it makes at that threshold. I will introduce the ROL curve, a close companion of ROC curves that allow to quantify the loss at a particular predicted positive rate. Rate-calibrated classifiers have an expected loss that is linearly related to AUC, which vindicates AUC as a coherent measure of classification performance (contrary to recent claims in the literature).
    ...
    University of Washington
    http://www.cs.washington.edu/homes/etzioni/
    ...
    Web Scale Slides
    Abstract:
    Information Extraction (IE) is the task of mapping natural-language sentences to machine-processable representations of the sentences' content. IE is often formulated as a machine-learning problem where an extractor for a particular relation (e.g., seminar speaker) is learned from labeled training examples. My talk will describe Open IE---an approach to scaling IE to the Web where the set of potential relations is not known in advance making a standard machine learning approach impossible. I will describe various bootstrapping approaches that enables us to utilize machine learning at Web scale.
    ...
    Oren Etzioni is the Washington Research Foundation Entrepreneurship Professor at the University of Washington's Computer Science Department. He received his bachelor's degree in Computer Science from Harvard University in June 1986 where he was the first Harvard student to "major" in Computer Science. Etzioni received his Ph.D. from Carnegie Mellon University in January 1991, and joined the University of Washington's faculty in February 1991, where he is now a Professor of Computer Science. Etzioni received a National Young Investigator Award in 1993, and was selected as a AAAI Fellow a decade later. In 2007, he received the Robert S. Engelmore Memorial Award. He is the founder and director of the University of Washington's Turing Center.
    Etzioni is the author of over 100 technical papers in a wide range of conferences including AAAI, ACL, CIDR, COLING, EMNLP, FOCS, HLT, ICML, IJCAI, ISWC, IUI, KDD, KR, SIGIR, and WWW. He is a founder of three companies and a Venture Partner at the Madrona Venture Group. His work has been featured in the New York Times, Wall Street Journal, NPR, SCIENCE, The Economist, TIME Magazine, Business Week, Newsweek, Discover Magazine, Forbes Magazine, Wired, NBC Nightly News, and even Pravda.

    (view changes)
    11:47 pm
  4. file Peter Flach.pdf uploaded
    11:45 pm
  5. file Oren Etzioni.pdf uploaded
    11:45 pm

Tuesday, December 13

  1. 10:25 pm
  2. page Album edited ... {Keynote2-1.JPG} {Keynote3.jpg} [image:IMG_0851.JPG width="200" height="20…
    ...
    {Keynote2-1.JPG}
    {Keynote3.jpg}
    [image:IMG_0851.JPG width="200" height="200"]{IMG_0851.JPG}
    eynote Talk 2
    Keynote Talk 3
    [align="center" link="@https://picasaweb.google.com/114446632343162094250/Tutorial1#"]
    Tutorial 1
    {IMG_0932.JPG}
    (view changes)
    10:25 pm

More