Advanced Search
DSpace@MIT

Browsing MIT Open Access Articles by Title

Research and Teaching Output of the MIT Community

Browsing MIT Open Access Articles by Title

Sort by: Order: Results:

  • Branavan, Satchuthanan R.; Chen, Harr; Eisenstein, Jacob; Barzilay, Regina (AI Access Foundation, 2009-04)
    This paper presents a new method for inferring the semantic properties of documents by leveraging free-text keyphrase annotations. Such annotations are becoming increasingly abundant due to the recent dramatic growth in ...
  • Meshi, Ofer; Sontag, David Alexander; Jaakkola, Tommi S.; Globerson, Amir (International Machine Learning Society, 2010-01)
    Many structured prediction tasks involve complex models where inference is computationally intractable, but where it can be well approximated using a linear programming relaxation. Previous approaches for learning for ...
  • Ghosh, Satrajit; Klein, Arno; Avants, Brian; Millman, Jarrod K. (Frontiers Research Foundation, 2012-04)
    Peer-reviewed publications are the primary mechanism for sharing scientific results. The current peer-review process is, however, fraught with many problems that undermine the pace, validity, and credibility of science. ...
  • Muslimin, Rizal (MIT Press, 2010-08)
    This project restructures weaving performance in architecture by analyzing the tacit knowledge of traditional weavers through perceptual study and converting it into an explicit rule in computational design. Three ...
  • Tan, Vincent Yan Fu; Anandkumar, Animashree; Willsky, Alan S. (Institute of Electrical and Electronics Engineers, 2010-04)
    The problem of learning tree-structured Gaussian graphical models from independent and identically distributed (i.i.d.) samples is considered. The influence of the tree structure and the parameters of the Gaussian distribution ...
  • Tan, Vincent Yan Fu; Sanghavi, Sujay; Fisher, John W., III; Willsky, Alan S. (Institute of Electrical and Electronics Engineers (IEEE), 2010-07)
    Sparse graphical models have proven to be a flexible class of multivariate probability models for approximating high-dimensional distributions. In this paper, we propose techniques to exploit this modeling ability for ...
  • Tan, Vincent Yan Fu; Anandkumar, Animashree; Willsky, Alan S. (MIT Press, 2011-05)
    The problem of learning forest-structured discrete graphical models from i.i.d. samples is considered. An algorithm based on pruning of the Chow-Liu tree through adaptive thresholding is proposed. It is shown that this ...
  • Branavan, S. R. K.; Kushman, Nathaniel A.; Lei, Tao; Barzilay, Regina (The Association for Computational Linguistics, 2012-07)
    Comprehending action preconditions and effects is an essential step in modeling the dynamics of the world. In this paper, we express the semantics of precondition relations extracted from text in terms of planning operations. ...
  • Colvin, Kimberly F.; Champaign, John; Liu, Alwina R.; Pritchard, David E.; Zhou, Qian; Fredericks, Colin (Athabasca University, 2014-09)
    We studied student learning in the MOOC 8.MReV Mechanics ReView, run on the edX.org open source platform. We studied learning in two ways. We administered 13 conceptual questions both before and after instruction, analyzing ...
  • Candogan, Utku Ozan; Ozdaglar, Asuman E.; Parrilo, Pablo A. (Institute of Electrical and Electronics Engineers (IEEE), 2011-12)
    Except for special classes of games, there is no systematic framework for analyzing the dynamical properties of multi-agent strategic interactions. Potential games are one such special but restrictive class of games that ...
  • Liao, Qianli; Leibo, Joel Z.; Poggio, Tomaso A. (Neural Information Processing Systems Foundation, 2013)
    One approach to computer object recognition and modeling the brain's ventral stream involves unsupervised learning of representations that are invariant to common transformations. However, applications of these ideas have ...
  • Daskalakis, Constantinos; Diakonikolas, Ilias; Servedio, Rocco A. (Society for Industrial and Applied Mathematics, 2012)
    A k-modal probability distribution over the domain {1,..., n} is one whose histogram has at most k "peaks" and "valleys." Such distributions are natural generalizations of monotone (k = 0) and unimodal (k = 1) probability ...
  • Collins, Michael; Singh-Miller, Natasha (Neural Information Processing Systems (NIPS) Foundation, 2009-12)
    We consider the problem of using nearest neighbor methods to provide a conditional probability estimate, P(y|a), when the number of labels y is large and the labels share some underlying structure. We propose a method ...
  • Hudson Kam, Carla L.; Ettlinger, Marc; Vytlacil, Jason; D'Esposito, Mark; Finn, Amy Sue (Frontiers Research Foundation, 2013-11)
    Does tuning to one's native language explain the “sensitive period” for language learning? We explore the idea that tuning to (or becoming more selective for) the properties of one's native-language could result in being ...
  • Choi, Myung Jin; Willsky, Alan S.; Tan, Vincent Y. F.; Anandkumar, Animashree (CrossRef test prefix, 2011-05)
    We study the problem of learning a latent tree graphical model where samples are available only from a subset of variables. We propose two consistent and computationally efficient algorithms for learning minimal latent ...
  • Canas, Guillermo D.; Poggio, Tomaso A.; Rosasco, Lorenzo Andrea (Neural Information Processing Systems Foundation, 2013-02)
    We study the problem of estimating a manifold from random samples. In particular, we consider piecewise constant and piecewise linear estimators induced by k-means and k-flats, and analyze their performance. We extend ...
  • Tellex, Stefanie A.; Thaker, Pratiksha R.; Joseph, Joshua Mason; Roy, Nicholas (Springer-Verlag, 2013-05)
    In order for robots to effectively understand natural language commands, they must be able to acquire meaning representations that can be mapped to perceptual features in the external world. Previous approaches to learning ...
  • Daskalakis, Constantinos; Diakonikolas, Ilias; Servedio, Rocco A. (Association for Computing Machinery (ACM), 2012-05)
    We consider a basic problem in unsupervised learning: learning an unknown Poisson Binomial Distribution. A Poisson Binomial Distribution (PBD) over {0,1,...,n} is the distribution of a sum of n independent Bernoulli random ...
  • Gavornik, Jeffrey P.; Shuler, Marshal G. Hussain; Loewenstein, Yonatan; Bear, Mark; Shouval, Harel Z. (National Academy of Sciences, 2009-04)
    The ability to represent time is an essential component of cognition but its neural basis is unknown. Although extensively studied both behaviorally and electrophysiologically, a general theoretical framework describing ...
  • Walter, Matthew R.; Hemachandra, Sachithra Madhaw; Homberg, Bianca S.; Tellex, Stefanie; Teller, Seth (Robotics: Science and Systems, 2013-06)
    This paper proposes an algorithm that enables robots to efficiently learn human-centric models of their environment from natural language descriptions. Typical semantic mapping approaches augment metric maps with higher-level ...
Open Access