Sciweavers

2944 search results - page 182 / 589
» Improving Bound Propagation
Sort
View
ESANN
2001
13 years 11 months ago
Penalized least squares, model selection, convex hull classes and neural nets
We develop improved risk bounds for function estimation with models such as single hidden layer neural nets, using a penalized least squares criterion to select the size of the mod...
Gerald H. L. Cheang, Andrew R. Barron
NIPS
2000
13 years 11 months ago
From Margin to Sparsity
We present an improvement of Noviko 's perceptron convergence theorem. Reinterpreting this mistakebound as a margindependent sparsity guarantee allows us to give a PAC{style ...
Thore Graepel, Ralf Herbrich, Robert C. Williamson
IJSYSC
1998
93views more  IJSYSC 1998»
13 years 10 months ago
A new adaptive control scheme with arbitrary nonlinear inputs
This paper presents a new analysis and design method for model reference adaptive control(MRAC) with arbitrary bounded input nonlinearities. The adaptive algorithm ensures that th...
Wen Yu, Manuel de la Sen
CORR
2011
Springer
148views Education» more  CORR 2011»
13 years 5 months ago
How well can we estimate a sparse vector?
The estimation of a sparse vector in the linear model is a fundamental problem in signal processing, statistics, and compressive sensing. This paper establishes a lower bound on t...
Emmanuel J. Candès, Mark A. Davenport
SIAMDM
2010
170views more  SIAMDM 2010»
13 years 5 months ago
Complete Minors and Independence Number
Let G be a graph with n vertices and independence number . Hadwiger's conjecture implies that G contains a clique minor of order at least n/. In 1982, Duchet and Meyniel prov...
Jacob Fox