Search
Now showing items 461-470 of 648
Learning From Snapshot Examples
(2005-04-13)
Examples are a powerful tool for teaching both humans and computers.In order to learn from examples, however, a student must first extractthe examples from its stream of perception. Snapshot learning is ageneral approach ...
Construction by robot swarms using extended stigmergy
(2005-04-08)
We describe a system in which simple, identical, autonomous robots assemble two-dimensional structures out of identical building blocks. We show that, in a system divided in this way into mobile units and structural units, ...
De-Emphasis of Distracting Image Regions Using Texture Power Maps
(2005-04-12)
A major obstacle in photography is the presence of distracting elements that pull attention away from the main subject and clutter the composition. In this article, we present a new image-processing technique that reduces ...
Identifying Expression Fingerprints using Linguistic Information
(2005-11-18)
This thesis presents a technology to complement taxation-based policy proposals aimed at addressing the digital copyright problem. Theapproach presented facilitates identification of intellectual propertyusing expression ...
Analysis of Perceptron-Based Active Learning
(2005-11-17)
We start by showing that in an active learning setting, the Perceptron algorithm needs $\Omega(\frac{1}{\epsilon^2})$ labels to learn linear separators within generalization error $\epsilon$. We then present a simple ...
Accurate and Scalable Surface Representation and Reconstruction from Images
(2005-11-18)
We introduce a new surface representation, the patchwork, to extend the problem of surface reconstruction from multiple images. A patchwork is the combination of several patches that are built one by one. This design ...
Conditional Random People: Tracking Humans with CRFs and Grid Filters
(2005-12-01)
We describe a state-space tracking approach based on a Conditional Random Field(CRF) model, where the observation potentials are \emph{learned} from data. Wefind functions that embed both state and observation into a space ...
Automatic Software Upgrades for Distributed Systems
(2005-11-30)
Upgrading the software of long-lived, highly-available distributed systems is difficult. It is not possible to upgrade all the nodes in a system at once, since some nodes may be unavailable and halting the system for an ...
Online Learning of Non-stationary Sequences
(2005-11-17)
We consider an online learning scenario in which the learner can make predictions on the basis of a fixed set of experts. We derive upper and lower relative loss bounds for a class of universal learning algorithms involving ...
On Field Constraint Analysis
(2005-11-03)
We introduce field constraint analysis, a new technique for verifying data structure invariants. A field constraint for a field is a formula specifying a set of objects to which the field can point. Field constraints ...