315 search results - page 12 / 63 » Structural Learning from Iconic Representations |
IDEAL
2005
Springer
14 years 3 months ago
2005
Springer
Artificial neural networks play an important role for pattern recognition tasks. However, due to poor comprehensibility of the learned network, and the inability to represent expl...
UAI
1998
13 years 11 months ago
1998
Dynamic probabilistic networks are a compact representation of complex stochastic processes. In this paper we examine how to learn the structure of a DPN from data. We extend stru...
CVPR
2007
IEEE
14 years 12 months ago
2007
IEEE
We present an algorithm, Hierarchical ISOmetric SelfOrganizing Map (H-ISOSOM), for a concise, organized manifold representation of complex, non-linear, large scale, high-dimension...
ECCV
2006
Springer
14 years 11 months ago
2006
Springer
Abstract. This paper addresses the problem of how to learn an appropriate feature representation from video to benefit video-based face recognition. By simultaneously exploiting th...
AI
2005
Springer
13 years 9 months ago
2005
Springer
The current research presents a system that learns to understand object names, spatial relation terms and event descriptions from observing narrated action sequences. The system e...