Advanced Search
DSpace@MIT

Browsing AI Memos (1959 - 2004) by Title

Research and Teaching Output of the MIT Community

Browsing AI Memos (1959 - 2004) by Title

Sort by: Order: Results:

  • Ghahramani, Zoubin; Jordan, Michael I. (1995-01-24)
    Real-world learning tasks often involve high-dimensional data sets with complex patterns of missing features. In this paper we review the problem of learning from incomplete data from two statistical perspectives---the ...
  • Olshausen, Bruno A. (1996-12-01)
    In previous work (Olshausen & Field 1996), an algorithm was described for learning linear sparse codes which, when trained on natural images, produces a set of basis functions that are spatially localized, oriented, ...
  • Winston, Patrick H. (1981-11-01)
    Much Learning is done by way of studying precedents and exercises. A teacher supplies a story, gives a problem, and expects a student both to solve a problem and to discover a principle. The student must find the ...
  • Miller, Erik G.; Tieu, Kinh; Stauffer, Chris P. (2001-09-01)
    We present a unifying framework in which "object-independent" modes of variation are learned from continuous-time data such as video sequences. These modes of variation can be used as "generators" to produce a manifold of ...
  • Ross, Michael G.; Kaelbling, Leslie Pack (2003-09-08)
    This memo describes the initial results of a project to create a self-supervised algorithm for learning object segmentation from video data. Developmental psychology and computational experience have demonstrated that the ...
  • Winston, Patrick H.; Binford, Thomas O.; Katz, Boris; Lowry, Michael (1982-11-01)
    It is too hard to tell vision systems what things look like. It is easier to talk about purpose and what things are for. Consequently, we want vision systems to use functional descriptions to identify things when ...
  • Finney, Sarah; Gardiol, Natalia H.; Kaelbling, Leslie Pack; Oates, Tim (2002-04-10)
    Most reinforcement learning methods operate on propositional representations of the world state. Such representations are often intractably large and generalize poorly. Using a deictic representation is believed to be ...
  • Martin, William A. (1968-02-01)
    Determination of the minimum resources required to parse a language generated by a given context free grammar is an intriguing and yet unsolved problem. It seems plausible that any unambiguous context free grammar could ...
  • Stein, Gideon P. (1996-12-01)
    This paper describes a new method for lens distortion calibration using only point correspondences in multiple views, without the need to know either the 3D location of the points or the camera locations. The standard ...
  • Waters, Richard C. (1983-02-01)
    Many loops can be more easily understood and manipulated if they are viewed as being built up out of operations on sequences of values. A notation is introduced which makes this viewpoint explicit. Using it, loops can ...
  • Bullwinkle, Candace (1977-05-01)
    This paper presents a discussion of means of describing the discourse and its components which makes speech act interpretation and reference disambiguation possible with minimal search of the knowledge in the database. ...
  • Beal, Jacob (2003-03-17)
    In a Communication Bootstrapping system, peer components with different perceptual worlds invent symbols and syntax based on correlations between their percepts. I propose that Communication Bootstrapping can also be ...
  • Dorr, Bonnie J. (1988-01-01)
    Current approaches to generation for machine translation make use of direct-replacement templates, large grammars, and knowledge-based inferencing techniques. Not only are rules language-specific, but they are too ...
  • Dorr, Bonnie J. (1989-06-01)
    This report introduces an implemented scheme for generating target- language sentences using a compositional representation of meaning called lexical conceptual structure. Lexical conceptual structure facilitates two crucial ...
  • McAllester, David; Siskind, Jeffrey (1991-12-01)
    Lifting is a well known technique in resolution theorem proving, logic programming, and term rewriting. In this paper we formulate lifting as an efficiency-motivated program transformation applicable to a wide variety ...
  • Christoudias, Chris Mario; Morency, Louis-Philippe; Darrell, Trevor (2003-04-18)
    Statistical shape and texture appearance models are powerful image representations, but previously had been restricted to 2D or simple 3D shapes. In this paper we present a novel 3D morphable model based on image-based ...
  • Richards, W.A. (1981-08-01)
    A lightness scale is derived from a theoretical estimate of the probability distribution of image intensities for natural scenes. The derived image intensity distribution considers three factors: reflectance, surface ...
  • Forbus, K. (1977-05-01)
    The perception of surface luster in achromatic single view images seems to depend on the existence of regions with source-like properties. These regions are due to the interaction of specular component of the surface's ...
  • Sarachik, Karen B. (1992-10-01)
    This paper presents a detailed error analysis of geometric hashing for 2D object recogition. We analytically derive the probability of false positives and negatives as a function of the number of model and image, ...
  • Moses, Yael; Ullman, Shimon (1991-05-01)
    Different approaches to visual object recognition can be divided into two general classes: model-based vs. non model-based schemes. In this paper we establish some limitation on the class of non model-based recognition ...
MIT-Mirage