Search Constraints

Start Over
Filtering by: Creator Herzing, Andrew A. Remove constraint Creator: Herzing, Andrew A. Advisor Tadepalli, Prasad Remove constraint Advisor: Tadepalli, Prasad

Search Results

  • Relation extraction with automatic ontonotes annotation and ETC

    Creator:
    Sauer, Andrew
    Abstract:
    Intuitively, it seems as though natural language processing tasks might benefit from explicit representations of the syntactic and semantic properties of text. Ontonotes is a dataset which attempts to annotate texts, to represent as much as possible of the meaning of the text explicitly within the annotation. Many tools exist...
    Resource Type:
    Honors College Thesis
    Full Text:
    Annotation and ETC by Andrew Sauer A THESIS submitted to Oregon State University Honors College in

  • Learning classification rules by randomized iterative local search

    Creator:
    Chisholm, Michael (Michael Andrew), 1974-
    Abstract:
    Learning easily understandable decision rules from examples is one of the classic problems in machine learning. Most learning algorithms for this problem employ some variation of a greedy separate-and-conquer algorithm. In this paper, we describe a system called LERILS that learns highly accurate and comprehensible rules from examples using a...
    Resource Type:
    Masters Thesis
    Full Text:
    variation of a greedy separate-and-conquer algorithm. In this paper, we describe a system called LERILS

  • New Directions in Search-based Structured Prediction: Multi-Task Learning and Integration of Deep Models

    Creator:
    Ma, Chao
    Abstract:
    This thesis studies the problem of structured prediction (SP), where the agent needs to predict a structured output for a given structured input (e.g., Part-of-Speech tagging sequence for an input sentence). Many important applications including machine translation in natural language processing (NLP) and image interpretation in computer vision can be...
    Resource Type:
    Dissertation
    Full Text:
    ), where the agent needs to predict a structured output for a given structured input (e.g., Part-of-Speech

  • Multi-criteria average reward reinforcement learning

    Creator:
    Natarajan, Sriraam
    Abstract:
    Reinforcement learning (RL) is the study of systems that learn from interaction with their environment. The current framework of Reinforcement Learning is based on receiving scalar rewards, which the agent aims to maximize. But in many real world situations, tradeoffs must be made among multiple objectives. This necessitates the use...
    Resource Type:
    Masters Thesis
    Full Text:
    preferences among multiple objectives. Learning a new policy for every possible weight vector is wasteful

  • Integrating learning and search for structured prediction

    Creator:
    Doppa, Janardhan Rao
    Abstract:
    We are witnessing the rise of the data-driven science paradigm, in which massive amounts of data - much of it collected as a side-effect of ordinary human activity - can be analyzed to make sense of the data and to make useful predictions. To fully realize the promise of this...
    Resource Type:
    Dissertation
    Full Text:
    – much of it collected as a side-effect of ordinary human activity – can be analyzed to make sense of

  • High-Dimensional Reinforcement Learning with Human Feedback

    Creator:
    Curran, William
    Abstract:
    State-of-the-art personal robots need to perform complex manipulation tasks to be viable in complex scenarios. However, many of these robots, like the PR2, use manipulators with high degrees of freedom. High degrees of freedom are desirable from a functionality standpoint, but make the learning task more difficult by adding a...
    Resource Type:
    Dissertation
    Full Text:
    degrees of freedom are desirable from a functionality standpoint, but make the learning task more

  • Bayesian methods for knowledge transfer and policy search in reinforcement learning

    Creator:
    Wilson, Aaron
    Abstract:
    How can an agent generalize its knowledge to new circumstances? To learn effectively an agent acting in a sequential decision problem must make intelligent action selection choices based on its available knowledge. This dissertation focuses on Bayesian methods of representing learned knowledge and develops novel algorithms that exploit the represented...
    Resource Type:
    Dissertation
    Full Text:
    an agent acting in a sequential decision problem must make intelligent action selection choices

  • Adversarial Attacks in Natural Language Question-Answering

    Creator:
    Rahurkar, Prachi S.
    Abstract:
    Question Answering in natural language processing has achieved significant progress in recent years. Yet, training and testing set methodology to evaluate the language models has proved inadequate. Adversarial examples aid us in finding loopholes inside these models and provide insights into their inner workings. In this work, an evaluation based...
    Resource Type:
    Masters Thesis
    Full Text:
    computer vision: A survey. IEEE Access, 6:14410–14430, 2018. [2] Anish Athalye, Logan Engstrom, Andrew

  • Local and Global Explanations for Deep Image Classification via Structured Attention Graphs

    Creator:
    Shitole, Vivswan
    Abstract:
    Attention maps are popular tools of explaining the decisions of convolutional neural net-works (CNNs) for image classification. Typically, for each image of interest, a single attention map is produced, which assigns weights to pixels based on their importance to the classification. We argue that a single attention map provides an...
    Resource Type:
    Masters Thesis
    Full Text:
    (CNNs) for image classification. Typically, for each image of interest, a single attention map is

  • Monte-Carlo planning for probabilistic domains

    Creator:
    Bjarnason, Ronald V.
    Abstract:
    This thesis presents a progression of novel planning algorithms that culminates in a new family of diverse Monte-Carlo methods for probabilistic planning domains. We provide a proof for performance guarantees and analyze how these algorithms can resolve some of the shortcomings of traditional probabilistic planning methods. The direct policy search...
    Resource Type:
    Dissertation
    Full Text:
    Fern This thesis presents a progression of novel planning algorithms that culminates in a new family