Sciweavers

495 search results - page 21 / 99
» Learning to generalize for complex selection tasks
Sort
View
CEC
2008
IEEE
14 years 1 months ago
Learning what to ignore: Memetic climbing in topology and weight space
— We present the memetic climber, a simple search algorithm that learns topology and weights of neural networks on different time scales. When applied to the problem of learning ...
Julian Togelius, Faustino J. Gomez, Jürgen Sc...
WAPCV
2007
Springer
14 years 25 days ago
Context Driven Focus of Attention for Object Detection
Abstract. Context plays an important role in general scene perception. In particular, it can provide cues about an object’s location within an image. In computer vision, object d...
Roland Perko, Ales Leonardis
JIRS
2007
120views more  JIRS 2007»
13 years 6 months ago
Optimal Camera Placement for Automated Surveillance Tasks
— Today, there are many opportunities to create vision-based intelligent systems that are human-centric. This is a very rich area because humans are very complex, and the number ...
Robert Bodor, Andrew Drenner, Paul R. Schrater, Ni...
VR
2008
IEEE
175views Virtual Reality» more  VR 2008»
13 years 6 months ago
Managing Visual Clutter: A Generalized Technique for Label Segregation using Stereoscopic Disparity
We present a new technique for managing visual clutter caused by overlapping labels in complex information displays. This technique, "label layering", utilizes stereosco...
Stephen Peterson, Magnus Axholt, Stephen R. Ellis
ECAI
2004
Springer
14 years 4 days ago
Piece-Wise Model Fitting Using Local Data Patterns
In this paper we propose a novel classification algorithm that fits models of different complexity on separate regions of the input space. The goal is to achieve a balance betwee...
Ricardo Vilalta, Murali-Krishna Achari, Christoph ...