Browse Dissertations and Theses - Computer Science by Title

  • Vulimiri, Ashish (2015-11-24)
    Wide-area Internet links are slow, expensive, and unreliable. This affects applications in two distinct ways. Back-end data processing applications, which need to transfer large amounts of data between data centers across ...

    application/pdf

    application/pdfPDF (2MB)
  • Li, Qiao (2001)
    ESD design rule checking is different from the conventional design rule checking in that not only different rules have to be applied for different components in the ESD protection circuit, but also style of layout is of ...

    application/pdf

    application/pdfPDF (5MB)Restricted to U of Illinois
  • Luhukay, Joseph F.P. (1983)
    The NMOS Gate-Cell, a regular structure that supports gate level implementations of random logic is introduced. It is an extension of the Weinberger array, where allowing input/output terminals on all four edges resulted ...

    application/pdf

    application/pdfPDF (4MB)Restricted to U of Illinois
  • Mallya, Arun Mohanray (2018-04-15)
    A key requirement for any agent that wishes to interact with the visual world is the ability to understand the behavior of objects in the scene, primarily through visual means. We humans, through our cognitive system, are ...

    application/pdf

    application/pdfPDF (49MB)Restricted Access
  • Yih, Wen-tau (2005)
    The proposed learning and inference frameworks have been applied to a variety of information extraction tasks, including entity extraction, entity/relation recognition, and semantic role labeling.

    application/pdf

    application/pdfPDF (3MB)Restricted to U of Illinois
  • 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)
  • Chan, Tak-Wai (1989)
    This thesis describes a new class of Intelligent Tutoring Systems (ITS) which I call the Learning Companion Systems (LCS). In the learning environment of such a system, there are three agents involved, namely, the human ...

    application/pdf

    application/pdfPDF (7MB)Restricted to U of Illinois
  • Perez, Eduardo (1997)
    When shortage of knowledge prevents human experts from choosing good attributes to represent empirical observations, learning is difficult. Expressing concepts by using only primitive (low-level) attributes is intricate ...

    application/pdf

    application/pdfPDF (11MB)Restricted to U of Illinois
  • Zhang, Ailing (2017-04-24)
    As an effective and provable primal method to estimate posterior distribution, Particle Mirror Descent is appealing for its simplicity and flexibility. In this thesis we explore the applications of Particle Mirror Descent ...

    application/pdf

    application/pdfPDF (1MB)
  • Rajpal, Shreya (2018-04-25)
    In this work, we present a novel methodology to recommend items that are compatible with a given item of clothing. Compatibility is a hard notion to capture because of its diversity and subjectivity. We propose an embedding ...

    application/pdf

    application/pdfPDF (134MB)
  • Zhang, Jianping (1990)
    This thesis describes an exploration of methods involved in learning flexible concepts that is an important and less explored area in machine learning. The two approaches described in this thesis are based on the idea of ...

    application/pdf

    application/pdfPDF (8MB)Restricted to U of Illinois
  • Mishra, Nina (1997)
    The third learning setting combines the first and second in that we both give our computer preclassified examples and allow it to pose membership queries. The unknown function f may now classify examples in one of three ...

    application/pdf

    application/pdfPDF (6MB)Restricted to U of Illinois
  • 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)
  • Falkenhainer, Brian Carl (1989)
    To make programs that understand and interact with the world as well as people do, we must duplicate the kind of flexibility people exhibit when conjecturing plausible explanations of the diverse physical phenomena they ...

    application/pdf

    application/pdfPDF (14MB)Restricted to U of Illinois
  • Wang, Liwei (2018-07-10)
    Computer vision is moving from predicting discrete, categorical labels to generating rich descriptions of visual data, in particular, in the form of natural language. Learning the joint latent representations for images ...

    application/pdf

    application/pdfPDF (25MB)
  • Kushal, Akash M. (2008)
    We also propose two different approaches for modeling the inter-part relations and algorithms for efficiently learning the model parameters. The first approach uses a generative model that models the joint probability ...

    application/pdf

    application/pdfPDF (2MB)Restricted to U of Illinois
  • Singh, Saurabh (2016-10-19)
    The world is full of tiny but useful objects such as the door handle of a car or the light switch in a room. Such objects are barely visible in an image and can be well approximated by a single point. We refer to these ...

    application/pdf

    application/pdfPDF (8MB)
  • McHenry, Kenton Guadron (2008)
    This dissertation addresses the task of learning to segment images into meaningful material and object categories. With regards to materials we consider the difficult task of segmenting objects made of transparent materials ...

    application/pdf

    application/pdfPDF (2MB)Restricted to U of Illinois
  • Vardhan, Abhay (2006)
    We show how the learning-based verification paradigm can be applied to a number of systems and for different kinds of specifications. First, we use learning to verify safety properties of finite state machines communicating ...

    application/pdf

    application/pdfPDF (4MB)Restricted to U of Illinois
  • Shin, Daeyun (2017-07-20)
    The goal of this study is to determine the effectiveness of different 3D shape representations in learning to generate volumetric shapes using deep neural networks. We propose to automatically reconstruct a 3D model from ...

    application/pdf

    application/pdfPDF (1MB)