2073 search results - page 123 / 415 » Learning for Dynamic Subsumption |
122
Voted
ICML
2010
IEEE
15 years 4 months ago
2010
IEEE
When modeling high-dimensional richly structured data, it is often the case that the distribution defined by the Deep Boltzmann Machine (DBM) has a rough energy landscape with man...
86
Voted
COMPLEXITY
2008
15 years 3 months ago
2008
Results are presented of a simulation which mimics an evolutionary learning process for small networks. Special features of these networks include a high recurrency, a transition ...
215
Voted
COLT
2010
Springer
15 years 1 months ago
2010
Springer
We present a new family of subgradient methods that dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative gradie...
141
click to vote
SASO
2008
IEEE
15 years 10 months ago
2008
IEEE
The distribution of data in large dynamic wireless sensor networks presents a difficult problem due to node mobility, link failures, and traffic congestion. In this paper, we pr...
117
click to vote
NIPS
2003
15 years 4 months ago
2003
We consider the question of predicting nonlinear time series. Kernel Dynamical Modeling (KDM), a new method based on kernels, is proposed as an extension to linear dynamical model...