Now showing items 1-13 of 13

    • Active Learning and Submodular Functions 

      Guillory, Andrew Russell (2012-09-13)
      Active learning is a machine learning setting where the learning algorithm decides what data is labeled. Submodular functions are a class of set functions for which many optimization problems have efficient exact or ...
    • Bayesian Computation and Optimal Decision Making in Primate Brains 

      Huang, Yanping
      This dissertation investigates the computational principles underlying the brains’ remarkable capacity to perceive, learn and act in environments of constantly varying uncertainty. Bayesian probability theory has suggested ...
    • Better Education Through Improved Reinforcement Learning 

      Mandel, Travis Scott
      When a new student comes to play an educational game, how can we determine what content to give them such that they learn as much as possible? When a frustrated customer calls in to a helpline, how can we determine what ...
    • Entity Analysis with Weak Supervision: Typing, Linking, and Attribute Extraction 

      Ling, Xiao
      With the advent of the Web, textual information has grown at an explosive rate. To digest this enormous amount of data, an automatic solution, Information Extraction (IE), has become necessary. Information extraction is a ...
    • Manipulators and Manipulation in high dimensional spaces 

      Kumar, Vikash
      Hand manipulation is one of the most complex form of biological movements. Despite its significance in multiple fields such as biomechanics, neuroscience, robotics and graphics, our understanding of dexterous manipulation ...
    • Natural Language as a Scaffold for Visual Recognition 

      Yatskar, Mark
      A goal of artificial intelligence is to create a system that can perceive and understand the visual world through images. Central to this goal is defining what exactly should be recognized, both in structure and coverage. ...
    • New Techniques in Deep Representation Learning 

      Andrew, Galen Michael
      The choice of feature representation can have a large impact on the success of a machine learning algorithm at solving a given problem. Although human engineers employing task-specific domain knowledge still play a key ...
    • Object Recognition and Semantic Scene Labeling for RGB-D Data 

      Lai, Kevin Kar Wai (2014-02-24)
      The availability of RGB-D (Kinect-like) cameras has led to an explosive growth of research on robot perception. RGB-D cameras provide high resolution (640 x 480) synchronized videos of both color (RGB) and depth (D) at 30 ...
    • Situated Learning and Understanding of Natural Language 

      Artzi, Yoav
      Robust language understanding systems have the potential to transform how we interact with computers. However, significant challenges in automated reasoning and learning remain to be solved before we achieve this goal. To ...
    • Span-based Neural Structured Prediction 

      Lee, Kenton
      A long-standing goal in artificial intelligence is for machines to understand natural language. With ever-growing amounts of data in the world, it is crucial to automate many aspects of language understanding so that users ...
    • The Intelligent Management of Crowd-Powered Machine Learning 

      Lin, Christopher
      Artificial intelligence and machine learning power many technologies today, from spam filters to self-driving cars to medical decision assistants. While this revolution has hugely benefited from algorithmic developments, ...
    • The Sum-Product Theorem and its Applications 

      Friesen, Abram
      Models in artificial intelligence (AI) and machine learning (ML) must be expressive enough to accurately capture the state of the world, but tractable enough that reasoning and inference within them is feasible. However, ...
    • Understanding human genome regulation through entropic graph-based regularization and submodular optimization 

      Libbrecht, Maxwell Wing
      I am interested in developing computational methods to improve understanding of human genome regulation. This thesis is organized around two novel machine learning methods. First, I present a new method in the field of ...