Sciweavers

3096 search results - page 213 / 620
» The Generalized FITC Approximation
Sort
View
EMNLP
2006
15 years 6 months ago
Loss Minimization in Parse Reranking
We propose a general method for reranker construction which targets choosing the candidate with the least expected loss, rather than the most probable candidate. Different approac...
Ivan Titov, James Henderson
SODA
2004
ACM
98views Algorithms» more  SODA 2004»
15 years 6 months ago
End-to-end packet-scheduling in wireless ad-hoc networks
Abstract Packet-scheduling is a particular challenge in wireless networks due to interference from nearby transmissions. A distance-2 interference model serves as a useful abstract...
V. S. Anil Kumar, Madhav V. Marathe, Srinivasan Pa...
NC
1998
101views Neural Networks» more  NC 1998»
15 years 6 months ago
Evolutionary Optimized Tensor Product Bernstein Polynomials versus Backpropagation Networks
In this paper a new approach for approximation problems involving only few input and output parameters is presented and compared to traditional Backpropagation Neural Networks (BP...
Günther R. Raidl, Gabriele Kodydek
NETWORKING
2000
15 years 6 months ago
Computing Blocking Probabilities in Multi-class Wavelength Routing Networks
We present an approximate analytical method to compute efficiently the call blocking probabilities in wavelength routing networks with multiple classes of calls. The model is fairl...
Sridhar Ramesh, George N. Rouskas, Harry G. Perros
159
Voted
GECCO
2008
Springer
170views Optimization» more  GECCO 2008»
15 years 6 months ago
Evolving prediction weights using evolution strategy
The evolution strategy is one of the strongest evolutionary algorithms for optimizing real-value vectors. In this paper, we study how to use it for the evolution of prediction wei...
Trung Hau Tran, Cédric Sanza, Yves Duthen