Search
Now showing items 101-110 of 136
Contextual Influences on Saliency
(2004-04-14)
This article describes a model for including scene/context priors in attention guidance. In the proposed scheme, visual context information can be available early in the visual processing chain, in order to modulate the ...
A 1020-Node Modular Microphone Array and Beamformer for Intelligent Computing Spaces
(2004-04-14)
Ubiquitous computing environments are characterized by an unboundedamount of noise and crosstalk. In these environments, traditionalmethods of sound capture are insufficient, and array microphones areneeded in order to ...
On Generalized Records and Spatial Conjunction in Role Logic
(2004-04-06)
We have previously introduced role logic as a notation fordescribing properties of relational structures in shapeanalysis, databases and knowledge bases. A natural fragmentof role logic corresponds to two-variable logic ...
Cascading Regularized Classifiers
(2004-04-21)
Among the various methods to combine classifiers, Boosting was originally thought as an stratagem to cascade pairs of classifiers through their disagreement. I recover the same idea from the work of Niyogi et al. to show ...
Methods and Experiments With Bounded Tree-width Markov Networks
(2004-12-30)
Markov trees generalize naturally to bounded tree-width Markov networks, onwhich exact computations can still be done efficiently. However, learning themaximum likelihood Markov network with tree-width greater than 1 is ...
On Decision Procedures for Set-Value Fields
(2004-11-30)
An important feature of object-oriented programming languages is the ability todynamically instantiate user-defined container data structures such as lists, trees,and hash tables. Programs implement such data structures ...
A general mechanism for tuning: Gain control circuits and synapses underlie tuning of cortical neurons
(2004-12-31)
Tuning to an optimal stimulus is a widespread property of neurons in cortex. We propose that such tuning is a consequence of normalization or gain control circuits. We also present a biologically plausible neural circuitry ...
Neural Voting Machines
(2004-12-31)
 Winner-take-all networks typically pick as winners that alternative with the largest excitatory input. This choice is far from optimal when there is uncertainty in the strength of the inputs, and when information is ...
Machine-Checkable Correctness Proofs forIntra-procedural Dataflow Analyses
(2004-12-16)
This technical report describes our experience using the interactive theorem proverAthena for proving the correctness of abstract interpretation-based dataflow analyses.For each analysis, our methodology requires the ...
Programming an Amorphous Computational Medium
(2004-09)
Amorphous computing considers the problem of controllingmillions of spatially distributed unreliable devices which communicateonly with nearby neighbors. To program such a system, we need a highleveldescription language ...