111 search results - page 6 / 23 » Predictive State Representations: A New Theory for Modeling ... |
CVPR
2007
IEEE
14 years 9 months ago
2007
IEEE
We introduce novel discriminative learning algorithms for dynamical systems. Models such as Conditional Random Fields or Maximum Entropy Markov Models outperform the generative Hi...
HIPC
2005
Springer
14 years 1 months ago
2005
Springer
We recently proposed a new approach to parallelization, by decomposing the time domain, instead of the conventional space domain. This improves latency tolerance, and we demonstrat...
AAAI
2011
12 years 7 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...
FIDJI
2003
Springer
14 years 21 days ago
2003
Springer
This paper introduces a new programming model for distributed systems, distributed composite objects (DCO), to meet efficient implementation, transparency, and performance demands ...
CDC
2008
IEEE
14 years 2 months ago
2008
IEEE
— This paper outlines a novel and feasible procedure to predict vertical motions for safe landing of unmanned aerial vehicles (UAVs) during maritime operations. In the presence o...