Computer Science and Artificial Intelligence Lab (CSAIL): Recent submissions
Now showing items 701-720 of 2625
-
Exact Reproduction of Colored Images
(MIT Artificial Intelligence Laboratory, 1980-12)The problem of producing a colored image from a colored original is analyzed. Conditions are determined for the production of an image, in which the colors cannot be distinguished from those in the original by a human ...
-
Steps Toward a Psycholinguistic Model of Language Production
(MIT Artificial Intelligence Laboratory, 1979-04)This paper discusses what it would mean to have a psychological model of the language production process: what such a model would have to account for, what it would use as evidence. It outlines and motivates one particular ...
-
Simulating a Semantic Network in LMS
(MIT Artificial Intelligence Laboratory, 1980-09-29)A semantic network is a collection of nodes and the links between them. The nodes represent concepts, functions and entities, and the links represent relationships between varoius nodes. Any semantic network must be supplied ...
-
Logical Control Theory Applied to Mechanical Arms
(MIT Artificial Intelligence Laboratory, 1979-02)A new control algorithm based upon Logical Control Theory is developed for mechanical manipulators. The controller uses discrete tesselations of state space and a finite set of fixed torques to regulate non-rehearsed ...
-
The Last Whole XGP Font Catalog
(MIT Artificial Intelligence Laboratory, 1980-03)
-
A Numerical Method for Shape-From-Shading From A Single Image
(MIT Artificial Intelligence Laboratory, 1979-01)The shape of an object can be determined from the shading in a single image by solving a first-order, non-linear partial differential equation. The method of characteristics can be used to do this, but it suffers from a ...
-
Worms of Ganymedes - Hazards of Image "Restoration"
(MIT Artificial Intelligence Laboratory, 1980-09)
-
Cognitive Security for Personal Devices
(2008-03-17)Humans should be able to think of computers as extensions of their body, as craftsmen do with their tools. Current security models, however, are too unlike those used in human minds---for example, computers authenticate ...
-
A Fair Power Domain for Actor Computations
(MIT Artificial Intelligence Laboratory, 1979-06)Actor-based languages feature extreme concurrency, allow side effects, and specify a form of fairness which permits unbounded nondeterminism. This makes it difficult to provide a satisfactory mathematical foundation for ...
-
Trajectory Analysis and Semantic Region Modeling Using A Nonparametric Bayesian Model
(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, ...
-
Two-stage Optimization Approach to Robust Model Predictive Control with a Joint Chance Constraint
(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 ...
-
Efficient Motion Planning Algorithm for Stochastic Dynamic Systems with Constraints on Probability of Failure
(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 ...
-
The J%JOIN Package
(MIT Artificial Intelligence Laboratory, 1971-04-02)The J%JOIN program creates links between the elements of a set of line segments on the basis of their geometric proximity. According to the value of the third argument, (T or NIL), the program will either place a set of ...
-
The Line Proposer P%PROPOSE1, and Additional Notes on "F%FEATUREPOINTS" and "GVERIFY1"
(MIT Artificial Intelligence Laboratory, 1971-04-02)The line proposer P%PROPOSE1 is described in the first part of this memo. It makes use of links provided by the J%JOIN program, in proposing possibly missing lines in a line drawing of simple plane-faced objects. The ...
-
What's What
(MIT Artificial Intelligence Laboratory, 1971-03)An outline of the modules used in the copy demonstration, the reasons for doing robotics, and some possible directions for further work.
-
Heterarchy in the M.I.T. Robot
(MIT Artificial Intelligence Laboratory, 1971-03)
-
How to Use .VSCAN
(MIT Artificial Intelligence Laboratory, 1971-03)
-
Transfer learning for image classification with sparse prototype representations
(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 ...
-
Learning Grammatical Models for Object Recognition
(2008-02-25)Many object recognition systems are limited by their inability to share common parts or structure among related object classes. This capability is desirable because it allows information about parts and relationships in ...
-
Exploiting Transport-Level Characteristics of Spam
(2008-02-15)In the arms race to secure electronic mail users and servers fromunsolicited messages (spam), the most successful solutions employtechniques that are difficult for spammers to circumvent. Thisresearch investigates the ...