7930 search results - page 609 / 1586 » Greedy in Approximation Algorithms |
149
click to vote
ESANN
2000
15 years 8 months ago
2000
: Recurrent neural networks possess interesting universal approximation capabilities, making them good candidates for time series modeling. Unfortunately, long term dependencies ar...
233
click to vote
UAI
1998
15 years 8 months ago
1998
In recent years there has been a flurry of works on learning Bayesian networks from data. One of the hard problems in this area is how to effectively learn the structure of a beli...
206
click to vote
OL
2007
15 years 6 months ago
2007
We propose an SQP-type algorithm for solving nonlinear second-order cone programming (NSOCP) problems. At every iteration, the algorithm solves a convex SOCP subproblem in which th...
200
click to vote
FOCS
2007
IEEE
16 years 1 months ago
2007
IEEE
We consider approximation algorithms for buy-at-bulk network design, with the additional constraint that demand pairs be protected against edge or node failures in the network. In...
223
click to vote
CVPR
2010
IEEE
16 years 3 months ago
2010
IEEE
Maximum a posteriori (MAP) inference in Markov Random Fields (MRFs) is an NP-hard problem, and thus research has focussed on either finding efficiently solvable subclasses (e.g. t...