Sciweavers

147 search results - page 21 / 30
» On the weight dynamics of recurrent learning
Sort
View
NPL
1998
135views more  NPL 1998»
13 years 8 months ago
Local Adaptive Subspace Regression
Abstract. Incremental learning of sensorimotor transformations in high dimensional spaces is one of the basic prerequisites for the success of autonomous robot devices as well as b...
Sethu Vijayakumar, Stefan Schaal
IROS
2007
IEEE
171views Robotics» more  IROS 2007»
14 years 2 months ago
A Kalman filter for robust outlier detection
— In this paper, we introduce a modified Kalman filter that can perform robust, real-time outlier detection in the observations, without the need for parameter tuning. Robotic ...
Jo-Anne Ting, Evangelos Theodorou, Stefan Schaal
ICML
2010
IEEE
13 years 9 months ago
Boosting Classifiers with Tightened L0-Relaxation Penalties
We propose a novel boosting algorithm which improves on current algorithms for weighted voting classification by striking a better balance between classification accuracy and the ...
Noam Goldberg, Jonathan Eckstein
ICML
2009
IEEE
14 years 9 months ago
Factored conditional restricted Boltzmann Machines for modeling motion style
The Conditional Restricted Boltzmann Machine (CRBM) is a recently proposed model for time series that has a rich, distributed hidden state and permits simple, exact inference. We ...
Graham W. Taylor, Geoffrey E. Hinton
DSMML
2004
Springer
14 years 2 months ago
Transformations of Gaussian Process Priors
Abstract. Gaussian process prior systems generally consist of noisy measurements of samples of the putatively Gaussian process of interest, where the samples serve to constrain the...
Roderick Murray-Smith, Barak A. Pearlmutter