Browse Dept. of Computer Science by Subject "machine learning"

  • Rothganger, Fredrick H. (2004-11)
    This thesis introduces a novel representation for three-dimensional (3D) objects in terms of local affine-invariant descriptors of their appearance and the spatial relationships between the corresponding affine regions. ...

    application/pdf

    application/pdfPDF (3Mb)
  • Yoo, Wucherl (2013-02-03)
    Applications may have unintended performance problems in spite of compiler optimizations, because of the complexity of the state of the art hardware technologies. Most modern processors incorporate multiple cores that have ...

    application/pdf

    application/pdfPDF (3Mb)
  • Do, Quang (2012-09-18)
    In this thesis, we study the importance of background knowledge in relation extraction systems. We not only demonstrate the benefits of leveraging background knowledge to improve the systems' performance but also propose ...

    application/pdf

    application/pdfPDF (614Kb)
  • Ratinov, Lev; Roth, Dan; Srikumar, Vivek (2008-01)
    The most fundamental problem in information retrieval is that of interpreting information needs of users, typically expressed in a short query. Using the surface level representation of the query is especially unsatisfactory ...

    application/pdf

    application/pdfPDF (226Kb)
  • Lim, Shiau Hong (2009-05-05)
    Incorporating additional information from our prior domain knowledge can be the key to solving difficult classification tasks, especially when the available training data is limited. The crucial stage of feature construction, ...

    application/pdf

    application/pdfPDF (733Kb)
  • Sarmiento, Alejandro (2004-12)
    This work addresses the problem of generating a motion strategy for solving a visibility-based task with a mobile robot equipped with sensors. In particular, the problem is to find a static object -- modeled with a probability ...

    application/pdf

    application/pdfPDF (2Mb)
  • Crisostomo Romero, Pedro Moises (2011-05-25)
    Hand detection on images has important applications on person activities recognition. This thesis focuses on PASCAL Visual Object Classes (VOC) system for hand detection. VOC has become a popular system for object detection, ...

    application/pdf

    application/pdfPDF (1Mb)
  • Tran, Du; Sorokin, Alexander; Forsyth, David (2008-03)
    This paper proposes a metric learning based approach for human activity recognition with two main objectives: (1) reject unfamiliar activities and (2) learn with few examples. We show that our approach outperforms all ...

    application/pdf

    application/pdfPDF (7Mb)
  • Wen, Zhen (2004-07)
    Human faces provide important cues of human activities. Thus they are useful for human-human communication, human-computer interaction (HCI) and intelligent video surveillance. Computational models for face analysis and ...

    application/pdf

    application/pdfPDF (3Mb)
  • Small, Kevin M. (2009-10-02)
    Statistical machine learning has become an integral technology for solving many informatics applications. In particular, corpus-based statistical techniques have emerged as the dominant paradigm for core natural language ...

    application/pdf

    application/pdfPDF (2Mb)
  • Rizzolo, Nicholas (2012-02-06)
    Machine learning (ML) is the study of representations and algorithms used for building functions that improve their behavior with experience. Today, researchers in many domains are applying ML to solve their problems when ...

    application/pdf

    application/pdfPDF (1Mb)
  • Garg, Pranav; Neider, Daniel; Madhusudan, P.; Roth, Dan (2015)
    Inductive invariants can be robustly synthesized using a learning model where the teacher is a program verifier who instructs the learner through concrete program configurations, classified as positive, negative, and ...

    application/pdf

    application/pdfPDF (597Kb)
  • Chang, Allan; Amir, Eyal (2005-11)
    We present new algorithms for learning a logical model of actions' effects and preconditions in partially observable domains. The algorithms maintain a logical representation of the set of possible action models after each ...

    application/pdf

    application/pdfPDF (197Kb)
  • Klementiev, Alexandre A. (2010-01-06)
    Recent technological advances have facilitated the collection and distribution of a plethora of increasingly diverse and complex data. Supervised learning has been able to provide the toolbox of choice for exploiting it ...

    application/pdf

    application/pdfPDF (4Mb)
  • Li, Xiaoming (2006-08)
    The growing complexity of modern processors has made the generation of highly efficient code increasingly difficult. Manual code generation is very time consuming, but it is often the only choice since the code generated ...

    application/pdf

    application/pdfPDF (857Kb)
  • Sukumar, Pritam (2013-08-22)
    This thesis presents an investigation of the Collection of Parts Model for object categorization. Multiclass categorization is performed using the Collections of Parts model. Results using Support Vector Machines, L1 ...

    application/pdf

    application/pdfPDF (934Kb)
  • Agarwal, Shivani (2005-05)
    The problem of ranking, in which the goal is to learn a real-valued ranking function that induces a ranking or ordering over an instance space, has recently gained attention in machine learning. A particular setting of ...

    application/pdf

    application/pdfPDF (861Kb)
  • Cheng, Hong (2008-05)
    Classification is a core method widely studied in machine learning, statistics, and data mining. A lot of classification methods have been proposed in literature, such as Support Vector Machines, Decision Trees, and Bayesian ...

    application/pdf

    application/pdfPDF (2Mb)
  • Mayhew, Stephen (2014-05-30)
    We begin by giving a comprehensive literature review that ties together many fields which have heretofore remained separate. We comment on the approaches from each field and show which algorithms are similar and which are ...

    application/pdf

    application/pdfPDF (306Kb)
  • Mahmud, M. M. Hassan (2008-07)
    The aim of transfer learning is to reduce sample complexity required to solve a learning task by using information gained from solving related tasks. Transfer learning has in general been motivated by the observation that ...

    application/pdf

    application/pdfPDF (848Kb)