Browse by Subject "Machine Learning"

  • Pu, Wen; Choi, Jaesik; Amir, Eyal; Espelage, Dorothy L. (2013-06-25)

    application/pdf

    application/pdfPDF (631kB)
  • Goldwasser, Dan (2013-02-03)
    In this work we take a first step towards Learning from Natural Instructions (LNI), a framework for communicating human knowledge to computer systems using natural language. In this framework the process of learning is ...

    application/pdf

    application/pdfPDF (1MB)
  • Vardhan, Abhay; Sen, Koushik; Viswanathan, Mahesh; Agha, Gul A. (2004-06)
    We present a novel approach for verifying safety properties of finite state machines communicating over unbounded FIFO channels that is based on applying machine learning techniques. We assume that we are given a model of ...

    application/pdf

    application/pdfPDF (336kB)
  • Zelenko, Dmitry (2003-12)
    The dissertation presents a number of novel machine learning techniques and applies them to information extraction. The study addresses several information extraction subtasks: part of speech tagging, entity extraction, ...

    application/pdf

    application/pdfPDF (921kB)
  • Juen, Joshua Paul Joseph (2015-08-18)
    Mobile devices contain sensors which allow continuous recording of a user's motion allowing the development of activity, fitness and health applications. With varied applications, the motion sensors present new privacy ...

    application/pdf

    application/pdfPDF (6MB)
  • Connor, Michael (2012-02-06)
    A fundamental step in sentence comprehension involves assigning semantic roles to sentence constituents. To accomplish this, the listener must parse the sentence, find constituents that are candidate arguments, and assign ...

    application/pdf

    application/pdfPDF (830kB)
  • Wei, Qin; Heidorn, P. Bryan; Freeland, Chris (2010-02-03)
    Taxonomic Name Recognition is prerequisite for more advanced processing and mining of full-text taxonomic literatures. This paper investigates three issues of current TNR tools in detail: (1) The difficulties and methods ...

    application/pdf

    application/pdfPDF (105kB)
  • Hodosh, Micah A (2015-11-25)
    Automatically describing an image with a concise natural language description is an ambitious and emerging task bringing together the Natural Language and Computer Vision communities. With any emerging task, the necessary ...

    application/pdf

    application/pdfPDF (34MB)
  • Qian, Minglun (2005-04)
    In this thesis, we propose a recurrent FIR neural network, develop a constrained formulation for neural network learning, study an e_cient violation guided backpropagation algorithm for solving the constrained formulation ...

    application/pdf

    application/pdfPDF (4MB)
  • Kehoe, Adam K.; Torvik, Vetle I. (ACM, 2016-06)
    We describe a classifier-enhanced nearest neighbor approach to assigning Medical Subject Headings (MeSH) to unlabeled documents using a combination of abstract similarities and direct citations to labeled MEDLINE records. ...

    application/pdf

    application/pdfPDF (303kB)
  • Butz, Martin (2004-09)
    Rule-based evolutionary online learning systems, often referred to as Michigan-style learning classifier systems (LCSs), were proposed nearly thirty years ago (Holland, 1976; Holland, 1977) originally calling them cognitive ...

    application/pdf

    application/pdfPDF (6MB)
  • Guo, Ruiqi (2014-09-16)
    Humans can understand scenes with abundant detail: they see layouts, surfaces, the shape of objects among other details. By contrast, many machine-based scene analysis algorithms use simple representation to parse scenes, ...

    application/pdf

    application/pdfPDF (28MB)
  • Chang, Kai-Wei (2015-04-23)
    The desired output in many machine learning tasks is a structured object, such as tree, clustering, or sequence. Learning accurate prediction models for such problems requires training on large amounts of data, making use ...

    application/pdf

    application/pdfPDF (2MB)
  • Srikumar, Vivek (2013-05-24)
    The problem of ascribing a semantic representation to text is an important one that can help text understanding problems like textual entailment. In this thesis, we address the problem of assigning a shallow semantic ...

    application/pdf

    application/pdfPDF (778kB)
  • Ji, Ming (2014-01-16)
    Real-world data entities are often connected by meaningful relationships, forming large-scale networks. With the rapid growth of social networks and online relational data, it is widely recognized that networked data are ...

    application/pdf

    application/pdfPDF (5MB)
  • Cai, Deng (2009)
    Spectral methods have recently emerged as a powerful tool for dimensionality reduction and manifold learning. These methods use information contained in the eigenvectors of a data affinity (\ie, item-item similarity) ...

    application/pdf

    application/pdfPDF (775kB)
  • Levine, Geoffrey C. (2012-02-06)
    In order for a machine learning effort to succeed, an appropriate model must be chosen. This is a difficult task in which one must balance flexibility, so that the model can capture the complexities of the domain, and ...

    application/pdf

    application/pdfPDF (3MB)
  • Wen, Bihan (2015-10-30)
    In recent years, sparse signal modeling, especially using the synthesis dictionary model, has received much attention. Sparse coding in the synthesis model is, however, NP-hard. Various methods have been proposed to learn ...

    application/pdf

    application/pdfPDF (9MB)
  • Kamalnath, Vishnu Nath (2013-08-22)
    This thesis deals with incorporating artificial intelligence into a humanoid robot by making a cognitive model of the learning process. The goal is to “teach” a specialized humanoid robot, the iCub robot, to solve any ...

    application/pdf

    application/pdfPDF (2MB)
  • Wang, Li-Lun (2012-09-18)
    Statistical machine learning has achieved great success in many fields in the last few decades. However, there remain classification problems that computers still struggle to match human performance. Many such problems ...

    application/pdf

    application/pdfPDF (3MB)