730 search results - page 14 / 146 » Learning for control from multiple demonstrations |
72
Voted
ICML
2004
IEEE
15 years 10 months ago
2004
IEEE
We present a generalization of the nonnegative matrix factorization (NMF), where a multilayer generative network with nonnegative weights is used to approximate the observed nonne...
CDC
2010
IEEE
14 years 4 months ago
2010
IEEE
The asymptotic behavior of stochastic gradient algorithms is studied. Relying on some results of differential geometry (Lojasiewicz gradient inequality), the almost sure pointconve...
80
Voted
ICANN
2010
Springer
14 years 10 months ago
2010
Springer
Abstract. In this paper we present a Reinforcement Learning (RL) approach with the capability to train neural adaptive controllers for complex control problems without expensive on...
INFOCOM
1993
IEEE
15 years 1 months ago
1993
IEEE
Worst-casebounds on delay and backlog are derived for leaky bucket constrained sessions in arbitrary topology networks of Generalized Processor Sharing (GPS) 10] servers. The inhe...
106
click to vote
FGR
2011
IEEE
14 years 1 months ago
2011
IEEE
Abstract— We propose here to acquire high resolution sequences of a person’s face using a pan-tilt-zoom (PTZ) network camera. This capability should prove helpful in forensic a...