9520 search results - page 1571 / 1904 » or 2011 |
235
click to vote
AAAI
2011
14 years 6 months ago
2011
Effective access to knowledge within large declarative memory stores is one challenge in the development and understanding of long-living, generally intelligent agents. We focus o...
212
click to vote
AAAI
2011
14 years 6 months ago
2011
Action modeling is an important skill for agents that must perform tasks in novel domains. Previous work on action modeling has focused on learning STRIPS operators in discrete, r...
251
click to vote
AAAI
2011
14 years 6 months ago
2011
Recently, a number of researchers have proposed spectral algorithms for learning models of dynamical systems—for example, Hidden Markov Models (HMMs), Partially Observable Marko...
177
click to vote
AAAI
2011
14 years 6 months ago
2011
We propose a fast batch learning method for linearchain Conditional Random Fields (CRFs) based on Newton-CG methods. Newton-CG methods are a variant of Newton method for high-dime...
226
click to vote
AAAI
2011
14 years 6 months ago
2011
Coarse-to-fine approaches use sequences of increasingly fine approximations to control the complexity of inference and learning. These techniques are often used in NLP and visio...