Search Constraints

Start Over
Filtering by: Alternative title ssim Technical note no. 195 Remove constraint Alternative title ssim: Technical note no. 195 Committee Member Tadepalli, Prasad Remove constraint Committee Member: Tadepalli, Prasad Resource Type Masters Thesis Remove constraint Resource Type: Masters Thesis

Search Results

  • Shrunken learning rates do not improve AdaBoost on benchmark datasets

    Creator:
    Forrest, Daniel L. K.
    Abstract:
    Recent work has shown that AdaBoost can be viewed as an algorithm that maximizes the margin on the training data via functional gradient descent. Under this interpretation, the weight computed by AdaBoost, for each hypothesis generated, can be viewed as a step size parameter in a gradient descent search. Friedman...
    Resource Type:
    Masters Thesis
    Full Text:
    on 28 benchmark datasets. The results show that reduced learning rates provide no statistically

  • Investigation of automatic construction of reactive controllers

    Creator:
    Westerberg, Caryl J.
    Abstract:
    In real-time control systems, the value of a control decision depends not only on the correctness of the decision but also on the time when that decision is available. Recent work in real-time decision making has used machine learning techniques to automatically construct reactive controllers, that is, controllers with little...
    Resource Type:
    Masters Thesis
    Full Text:
    automatically construct reactive controllers, that is, controllers with little or no internal state and low

  • Using Change Representations to Analyze Properties of Variational Software

    Creator:
    Wang, Xiangyu
    Abstract:
    Appropriate representations of variational software simplify the analysis of their properties.This thesis proposes tailored representations of two kinds variational softwares: difference files of merge commits in Git and feature models. For the former, we use the Choice Edit Model, which is based on the choice calculus, to represent changes introduced...
    Resource Type:
    Masters Thesis
    Full Text:
    repositories shows that in some cases about 10% of merge conflicts having no semantical effects. For feature

  • Protein secondary structure prediction using conditional random fields and profiles

    Creator:
    Shen, Rongkun
    Abstract:
    Protein secondary structure prediction plays a pivotal role in predicting protein folding in three-dimensions. Its task is to assign each residue one of the three secondary structure classes helix, strand, or random coil. This is an instance of the problem of sequential supervised learning in machine learning. This thesis describes...
    Resource Type:
    Masters Thesis
    Full Text:
    , respectively. In addition, there was no apparent overfitting problem observed in our model. Besides

  • Active learning of constraints for semi-supervised clustering

    Creator:
    Xiong, Sicheng
    Abstract:
    Semi-supervised clustering aims to improve clustering performance by considering user supervision in the form of pairwise constraints. In this paper, we study the active learning problem of selecting pairwise must-link and cannot-link constraints for semisupervised clustering. We consider active learning in an iterative manner where in each iteration queries are...
    Resource Type:
    Masters Thesis
    Full Text:
    have cannot-link constraints between one another. Note that if there exists no cannot-link constraints

  • Learning greedy policies for the easy-first framework

    Creator:
    Xie, Jun
    Abstract:
    Easy-first, a search-based structured prediction approach, has been applied to many NLP tasks including dependency parsing and coreference resolution. This approach employs a learned greedy policy (action scoring function) to make easy decisions first, which constrains the remaining decisions and makes them easier. This thesis studies the problem of learning...
    Resource Type:
    Masters Thesis
    Full Text:
    ) = w · φ(a), where w is the weight vector and φ(·) is a predefined feature function. Note that the

  • D₊₊ : Structural Credit Assignment in Tightly Coupled Multiagent Domains

    Creator:
    Rahmattalabi, Aida
    Abstract:
    Autonomous multiagent teams can be used in complex exploration tasks to both expedite the exploration and improve the efficiency. However, use of multiagent systems presents additional challenges. Specifically, in domains where the agents' actions are tightly coupled, coordinating multiple agents to achieve cooperative behavior at the group level is difficult....
    Resource Type:
    Masters Thesis
    Full Text:
    , the agents receive no learning signal from the environment until they actually accomplish the task

  • Learning MDP action models via discrete mixture trees

    Creator:
    Wynkoop, Michael S.
    Abstract:
    This thesis addresses the problem of learning dynamic Bayesian network (DBN) models to support reinforcement learning. It focuses on learning regression tree models of the conditional probability distributions of the DBNs. Existing algorithms presume that the stochasticity in the domain can be modeled as a deterministic function with additive noise....
    Resource Type:
    Masters Thesis
    Full Text:
    work supported by the Defense Advanced Research Projects Agency (DARPA) under Contract No. FA8750-05-2

  • A Benchmarking Study of Unsupervised Anomaly Detection Algorithms

    Creator:
    Emmott, Andrew F.
    Abstract:
    It is common practice in the unsupervised anomaly detection literature to create experimental benchmarks by sampling from existing supervised learning datasets. We seek to improve this practice by identifying four dimensions important to real-world anomaly detection applications --- point difficulty, clusteredness of anomalies, relevance of features, and relative frequency of...
    Resource Type:
    Masters Thesis
    Full Text:
    distribution. While this is no different than binary classification in theory, two important differences are

  • Learning multiple non-redundant codebooks with word clustering for document classification

    Creator:
    Surve, Akshat Sudhakar
    Abstract:
    The problem of document classification has been widely studied in machine learning and data mining. In document classification, most of the popular algorithms are based on the bag-of-words representation. Due to the high dimensionality of the bag-of-words representation, significant research has been conducted to reduce the dimensionality via different approaches....
    Resource Type:
    Masters Thesis
    Full Text:
    other words, the results can be justified on a mathematical level but have ambiguous or no meaning in