Advanced Search
DSpace@MIT

Browsing CSAIL Technical Reports (July 1, 2003 - present) by Title

Research and Teaching Output of the MIT Community

Browsing CSAIL Technical Reports (July 1, 2003 - present) by Title

Sort by: Order: Results:

  • Rohanimanesh, Khashayar; Roy, Nicholas; Tedrake, Russ (2007-11-01)
    Choosing features for the critic in actor-critic algorithms with function approximation is known to be a challenge. Too few critic features can lead to degeneracy of the actor gradient, and too many features may lead to ...
  • Rahul, Hariharan; Kasbekar, Mangesh; Sitaraman, Ramesh; Berger, Arthur (2005-11-01)
    Prior analyses of the benefits of routing overlays are based onplatforms consisting of nodes located primarily in North America, onthe academic Internet, and at the edge of the network. This paper isthe first global study ...
  • Geiger, Gadi; Amara, Domenic G (2005-10-18)
    Previous studies have shown that dyslexic individuals who supplement windowed reading practice with intensive small-scale hand-eye coordination tasks exhibit marked improvement in their reading skills. Here we examine ...
  • Kollar, Thomas; Dickerson, Steven; Tellex, Stefanie; Banerjee, Ashis Gopal; Walter, Matthew R.; Teller, Seth; Roy, Nicholas (2011-02-01)
    We describe a new model for understanding hierarchical natural language commands for robot navigation and manipulation. The model has three components: a semantic structure that captures the hierarchical structure of ...
  • Glover, Jared; Kaelbling, Leslie Pack (2013-03-27)
    A deterministic method for sequential estimation of 3-D rotations is presented. The Bingham distribution is used to represent uncertainty directly on the unit quaternion hypersphere. Quaternions avoid the degeneracies of ...
  • Chachulski, Szymon; Jennings, Michael; Katti, Sachin; Katabi, Dina (2007-02-23)
    Opportunistic routing is a recent technique that achieves high throughput in the face of lossy wireless links. The current opportunistic routing protocol, ExOR, ties the MAC with routing, imposing a strict schedule on ...
  • Woodrow, Stephen Robert (2011-08-06)
    This thesis analyzes and discusses the effectiveness of social efforts to achieve collective action amongst Internet network operators in order to manage the growth of the Internet routing table. The size and rate of growth ...
  • Grimson, Eric; Wang, Xiaogang; Ng, Gee-Wah; Ma, Keng Teck (2008-06-24)
    We propose a novel nonparametric Bayesian model, Dual Hierarchical Dirichlet Processes (Dual-HDP), for trajectory analysis and semantic region modeling in surveillance settings, in an unsupervised way. In our approach, ...
  • Agarwal, Shivani (2008-08-07)
    In ranking, one is given examples of order relationships among objects, and the goal is to learn from these examples a real-valued ranking function that induces a ranking or ordering over the object space. We consider the ...
  • Urtasun, Raquel; Quattoni, Ariadna; Darrell, Trevor (2007-11-06)
    When a series of problems are related, representations derived fromlearning earlier tasks may be useful in solving later problems. Inthis paper we propose a novel approach to transfer learning withlow-dimensional, non-linear ...
  • Quattoni, Ariadna; Collins, Michael; Darrell, Trevor (2008-03-03)
    To learn a new visual category from few examples, prior knowledge from unlabeled data as well as previous related categories may be useful.  We develop a new method for transfer learning which exploits available unlabeled ...
  • Urtasun, Raquel; Quattoni, Ariadna; Lawrence, Neil; Darrell, Trevor (2008-04-11)
    When a series of problems are related, representations derived from learning earlier tasks may be useful in solving later problems. In this paper we propose a novel approach to transfer learning with low-dimensional, ...
  • Weitzner, Daniel J.; Abelson, Harold; Berners-Lee, Tim; Hanson, Chris; Hendler, James; Kagal, Lalana; McGuinness, Deborah L.; Sussman, Gerald Jay; Waterman, K. Krasnow (2006-01-27)
    Attempts to address issues of personal privacy in a world of computerized databases and information networks -- from security technology to data protection regulation to Fourth Amendment law jurisprudence -- typically ...
  • Choi, Myung Jin; Lim, Joseph J.; Torralba, Antonio; Willsky, Alan S. (2010-10-29)
    There has been a growing interest in exploiting contextual information in addition to local features to detect and localize multiple object categories in an image. A context model can rule out some unlikely combinations ...
  • Ono, Masahiro; Williams, Brian C. (2008-03-06)
    When controlling dynamic systems such as mobile robots in uncertain environments, there is a trade off between risk and reward. For example, a race car can turn a corner faster by taking a more challenging path. This paper ...
  • Zhao, Qin; Rabbah, Rodric; Amarasinghe, Saman; Rudolph, Larry; Wong, Weng-Fai (2006-09-25)
    Modern memory systems play a critical role in the performance ofapplications, but a detailed understanding of the application behaviorin the memory system is not trivial to attain. It requires timeconsuming simulations of ...
  • Hung, Chou; Kreiman, Gabriel; Poggio, Tomaso; DiCarlo, James J. (2005-07-06)
    Understanding the complex brain computations leading to object recognition requires quantitatively characterizing the information represented in inferior temporal cortex (IT), the highest stage of the primate visual stream. ...
  • Freeman, William; Durand, Fredo; Weiss, Yair; Levin, Anat (2009-03-31)
    Blind deconvolution is the recovery of a sharp version of a blurred image when the blur kernel is unknown. Recent algorithms have afforded dramatic progress, yet many aspects of the problem remain challenging and hard to ...
  • Miller, Rob; Karger, David; Marcus, Adam; Bernstein, Michael (2009-10-07)
    To find interesting, personally relevant web content, we often rely on friends and colleagues to pass links along as they encounter them. In this paper, we study and augment link-sharing via e-mail, the most popular means ...
  • Levin, Anat; Freeman, William T.; Durand, Fredo (2008-04-16)
    Computer vision has traditionally focused on extracting structure,such as depth, from images acquired using thin-lens or pinhole optics. The development of computational imaging is broadening this scope; a variety of ...
MIT-Mirage