Sciweavers

1837 search results - page 192 / 368
» Learning From Ambiguous Examples
Sort
View
ICCV
2007
IEEE
16 years 19 days ago
Deformable Template As Active Basis
This article proposes an active basis model and a shared pursuit algorithm for learning deformable templates from image patches of various object categories. In our generative mod...
Ying Nian Wu, Zhangzhang Si, Chuck Fleming, Song C...
AH
2008
Springer
16 years 20 days ago
A Validation Framework for Formal Models in Adaptive Work-Integrated Learning
The focus of my thesis is on the development of a multi-method framework for the validation of formal models (domain model, user model, and teaching model) for adaptive work-integr...
Barbara Kump
COLT
1999
Springer
15 years 10 months ago
Regret Bounds for Prediction Problems
We present a unified framework for reasoning about worst-case regret bounds for learning algorithms. This framework is based on the theory of duality of convex functions. It brin...
Geoffrey J. Gordon
111
Voted
NIPS
2001
15 years 7 months ago
Scaling Laws and Local Minima in Hebbian ICA
We study the dynamics of a Hebbian ICA algorithm extracting a single non-Gaussian component from a high-dimensional Gaussian background. For both on-line and batch learning we fin...
Magnus Rattray, Gleb Basalyga
EUROCAST
2007
Springer
182views Hardware» more  EUROCAST 2007»
16 years 15 days ago
A k-NN Based Perception Scheme for Reinforcement Learning
Abstract a paradigm of modern Machine Learning (ML) which uses rewards and punishments to guide the learning process. One of the central ideas of RL is learning by “direct-online...
José Antonio Martin H., Javier de Lope Asia...