Sciweavers

131 search results - page 2 / 27
» Resolving Variations in Learning Spaces for Experiential Lea...
Sort
View
COLT
2008
Springer
13 years 6 months ago
Extracting Certainty from Uncertainty: Regret Bounded by Variation in Costs
Prediction from expert advice is a fundamental problem in machine learning. A major pillar of the field is the existence of learning algorithms whose average loss approaches that ...
Elad Hazan, Satyen Kale
CVPR
2007
IEEE
14 years 6 months ago
Variational Bayes Based Approach to Robust Subspace Learning
This paper presents a new algorithm for the problem of robust subspace learning (RSL), i.e., the estimation of linear subspace parameters from a set of data points in the presence...
Takayuki Okatani, Koichiro Deguchi
JMLR
2010
136views more  JMLR 2010»
12 years 11 months ago
Approximate Riemannian Conjugate Gradient Learning for Fixed-Form Variational Bayes
Variational Bayesian (VB) methods are typically only applied to models in the conjugate-exponential family using the variational Bayesian expectation maximisation (VB EM) algorith...
Antti Honkela, Tapani Raiko, Mikael Kuusela, Matti...
DSP
2007
13 years 4 months ago
Blind separation of nonlinear mixtures by variational Bayesian learning
Blind separation of sources from nonlinear mixtures is a challenging and often ill-posed problem. We present three methods for solving this problem: an improved nonlinear factor a...
Antti Honkela, Harri Valpola, Alexander Ilin, Juha...
CEC
2005
IEEE
13 years 10 months ago
Sensorimotor experience and its metrics: informational geometry and the temporal horizon
Abstract- We introduce metrics on sensorimotor experience at various temporal scales based on informationtheory. Sensorimotor variables through which the experience of an agent fl...
Chrystopher L. Nehaniv