mirage

Browsing by Author "Dietterich, Thomas Glen"

DSpace/Manakin Repository

Browsing by Author "Dietterich, Thomas Glen"

Sort by: Order: Results:

  • AO* revisited 
    Bayer-Zubek, Valentina; Dietterich, Thomas Glen (2004-06-30)
    This paper revisits the AO* algorithm introduced by Martelli and Montanari [1] and made popular by Nilsson [2] The paper's main contributions are: (1) proving that the value of a node monotonically increases as the AO* s ...
  • Bootstrap methods for the cost-sensitive evaluation of classifiers 
    Oregon State University. Dept. of Computer Science; Margineantu, Dragos D. (Dragos Dorin); Dietterich, Thomas Glen (Corvallis, OR : Oregon State University, Dept. of Computer Science, 2000)
    Many machine learning applications require classifiers that minimize an asymmetric cost function rather than the misclassification rate, and several recent papers have addressed this problem. However, these papers h ...
  • Exploiting monotonicity via logistic regression in Bayesian network learning 
    Oregon State University. Dept. of Computer Science; Restificar, Angelo C.; Dietterich, Thomas Glen (Corvallis, OR : Oregon State University, Dept. of Computer Science, 2013-01-29)
    An important challenge in machine learning is to find ways of learning quickly from very small amounts of training data. The only way to learn from small data samples is to constrain the learning process by exploiting ba ...
  • Improving SVM accuracy by training on auxiliary data sources 
    Oregon State University. Dept. of Computer Science; Wu, Pengcheng; Dietterich, Thomas Glen (Corvallis, OR : Oregon State University, Dept. of Computer Science, 2004)
    The standard model of supervised learning assumes that training and test data are drawn from the same underlying distribution. This paper explores an application in which a second, auxiliary, source of data is available ...
  • Integrating learning from examples into the search for diagnostic policies 
    Oregon State University. Dept. of Computer Science; Bayer-Zubek, Valentina; Dietterich, Thomas Glen (Corvallis, OR : Oregon State University, Dept. of Computer Science, 2004)
    This paper studies the problem of learning diagnostic policies from training examples. A diagnostic policy is a complete description of the decision-making actions of a diagnostician (i.e., tests followed by a diagnostic ...
  • Interacting meaningfully with machine learning systems : three experiments 
    Oregon State University. Dept. of Computer Science; Stumpf, Simone; Rajaram, Vidya; Li, Lida; Wong, Weng-Keen; Burnett, Margaret, 1949-; Dietterich, Thomas Glen; Sullivan, Erin; Herlocker, Jonathan Lee (Corvallis, OR : Oregon State University, Dept. of Computer Science, 2007)
    Although machine learning is becoming commonly used in today's software, there has been little research into how end users might interact with machine learning systems, beyond communicating simple "right/wrong" judgments ...
  • Learning and reasoning 
    Oregon State University. Dept. of Computer Science; Dietterich, Thomas Glen (Corvallis, OR : Oregon State University, Dept. of Computer Science, 2003-05-26)
    What is the relationship between learning and reasoning? Much recent work in machine learning has been criticized for focusing on learning and ignoring reasoning. This paper attempts to describe the various ways in which ...
  • Machine learning for cognitive networks : technology assessment and research challenges 
    Oregon State University. Dept. of Computer Science; Dietterich, Thomas Glen; Langley, Pat (Corvallis, OR : Oregon State University, Dept. of Computer Science, 2003-05-11)
    The field of machine learning has made major strides over the last 20 years. This document summarizes the major problem formulations that the discipline has studied, then reviews three tasks in cognitive networking and b ...
  • A POMDP approximation algorithm that anticipates the need to observe 
    Oregon State University. Dept. of Computer Science; Bayer, Valentina; Dietterich, Thomas Glen (Corvallis, OR : Oregon State University, Dept. of Computer Science, 2000)
    This paper introduces the even-odd POMDP, an approximation to POMDPs in which the world is assumed to be fully observable every other time step. The even-odd POMDP can be converted into an equivalent MDP, the 2MDP, whos ...
  • A POMDP approximation algorithm that anticipates the need to observe 
    Oregon State University. Dept. of Computer Science; Zubek, Valentina Bayer; Dietterich, Thomas Glen (Corvallis, OR : Oregon State University, Dept. of Computer Science, 2004-07-05)
    This paper introduces the even-odd POMDP an approximation to POMDPs Partially Observable Markov Decision Problems in which the world is assumed to be fully observable every other time step. This approximation works wel ...
  • Proposed metrics for transfer learning 
    Oregon State University. Dept. of Computer Science; Dietterich, Thomas Glen (Corvallis, OR : Oregon State University, Dept. of Computer Science, 2006-04-30)
    Summary: Four proposed metrics: [1] average relative reduction in training time (sample size, number of training experiences) [2] jumpstart (initial advantage of transfer algorithm) [3] handicap (how long it takes the ...
  • Pruning improves heuristic search for cost-sensitive learning 
    Oregon State University. Dept. of Computer Science; Zubek, Valentina Bayer; Dietterich, Thomas Glen (Corvallis, OR : Oregon State University, Dept. of Computer Science, 2004)
    This paper addresses cost-sensitive classification in the setting where there are costs for measuring each attribute as well as costs for misclassification errors. We show how to formulate this as a Markov Decision Proc ...
  • Recovery from interruptions : knowledge workers' strategies, failures and envisioned solutions 
    Oregon State University. Dept. of Computer Science; Stumpf, Simone; Burnett, Margaret, 1949-; Dietterich, Thomas Glen; Johnsrude, Kevin; Herlocker, Jonathan Lee (Corvallis, OR : Oregon State University, Dept. of Computer Science, 2005)
    This paper presents qualitative results from interviews with knowledge workers about their recovery strategies after interruptions. Special focus is given to when these strategies fail due to the nature of the interrupti ...
  • Toward harnessing user feedback for machine learning 
    Oregon State University. Dept. of Computer Science; Stumpf, Simone; Rajaram, Vidya; Li, Lida; Burnett, Margaret, 1949-; Dietterich, Thomas Glen; Sullivan, Erin; Drummond, Russell; Herlocker, Jonathan Lee (Corvallis, OR : Oregon State University, Dept. of Computer Science, 2006-10-02)
    There has been little research into how end users might be able to communicate advice to machine learning systems. If this resource--the users themselves--could somehow work hand-in-hand with machine learning systems, th ...
  • Training conditional random fields via gradient tree boosting 
    Dietterich, Thomas Glen; Ashenfelter, Adam J.; Bulatov, Yaroslav (2004)
    Conditional Random Fields (CRFs; Lafferty, McCallum, & Pereira, 2001) provide a flexible and powerful model for learning to assign labels to elements of sequences in such applications as part-of-speech tagging, text-to ...
  • Two heuristics for solving POMDPs having a delayed need to observe 
    Oregon State University. Dept. of Computer Science; Zubek, Valentina Bayer; Dietterich, Thomas Glen (Corvallis, OR : Oregon State University, Dept. of Computer Science, 2004)
    A common heuristic for solving Partially Observable Markov Decision Problems POMDPs is to first solve the underlying Markov Decision Process MDP and then construct a POMDP policy by performing a fixed depth lookahead sea ...

Search ScholarsArchive@OSU

Browse

My Account