3256 search results - page 219 / 652 » Learning Linear Transformations |
162
click to vote
GECCO
2005
Springer
16 years 23 hour ago
2005
Springer
Existing Recurrent Neural Networks (RNNs) are limited in their ability to model dynamical systems with nonlinearities and hidden internal states. Here we use our general framework...
178
click to vote
ICML
2007
IEEE
16 years 7 months ago
2007
IEEE
Many kernel learning methods have to assume parametric forms for the target kernel functions, which significantly limits the capability of kernels in fitting diverse patterns. Som...
180
click to vote
ICRA
1995
IEEE
15 years 10 months ago
1995
IEEE
This paper presents a method of vision-based reinforcement learning by which a robot learns to shoot a ball into a goal, and discusses several issues in applying the reinforcement...
169
click to vote
CVPR
2008
IEEE
16 years 8 months ago
2008
IEEE
We present a novel approach to non-rigid structure from motion (NRSFM) from an orthographic video sequence, based on a new interpretation of the problem. Existing approaches assum...
177
click to vote
ICML
2007
IEEE
16 years 7 months ago
2007
IEEE
Nonlinear ICA may not result in nonlinear blind source separation, since solutions to nonlinear ICA are highly non-unique. In practice, the nonlinearity in the data generation pro...