2875 search results - page 342 / 575 » Distributed Reactive Machines |
160
click to vote
ICML
2009
IEEE
16 years 5 months ago
2009
IEEE
In this paper, we investigate a simple, mistakedriven learning algorithm for discriminative training of continuous density hidden Markov models (CD-HMMs). Most CD-HMMs for automat...
143
click to vote
ICML
2007
IEEE
16 years 5 months ago
2007
IEEE
A new hierarchical nonparametric Bayesian model is proposed for the problem of multitask learning (MTL) with sequential data. Sequential data are typically modeled with a hidden M...
141
click to vote
ICML
2007
IEEE
16 years 5 months ago
2007
IEEE
Hierarchical models have been extensively studied in various domains. However, existing models assume fixed model structures or incorporate structural uncertainty generatively. In...
157
click to vote
ICML
2007
IEEE
16 years 5 months ago
2007
IEEE
The UCT algorithm learns a value function online using sample-based search. The TD() algorithm can learn a value function offline for the on-policy distribution. We consider three...
140
click to vote
ICML
2007
IEEE
16 years 5 months ago
2007
IEEE
Given a large, real graph, how can we generate a synthetic graph that matches its properties, i.e., it has similar degree distribution, similar (small) diameter, similar spectrum,...