Sciweavers

1974 search results - page 279 / 395
» On Unbiased Linear Approximations
Sort
View
ML
2002
ACM
168views Machine Learning» more  ML 2002»
14 years 9 months ago
On Average Versus Discounted Reward Temporal-Difference Learning
We provide an analytical comparison between discounted and average reward temporal-difference (TD) learning with linearly parameterized approximations. We first consider the asympt...
John N. Tsitsiklis, Benjamin Van Roy
TIT
1998
96views more  TIT 1998»
14 years 9 months ago
Nonparametric Estimation of Transfer Functions: Rates of Convergence and Adaptation
Abstract— The paper deals with estimating transfer functions of stable linear time-invariant systems under stochastic assumptions. We adopt a nonparametric minimax approach for m...
Alexander Goldenshluger
NCA
2007
IEEE
14 years 9 months ago
A computational strategy exploiting genetic algorithms to recover color surface reflectance functions
—Information about the spectral reflectance of a color surface is useful in many applications. Assuming that reflectance functions can be adequately approximated by a linear comb...
Raimondo Schettini, Silvia Zuffi
SCHOLARPEDIA
2008
109views more  SCHOLARPEDIA 2008»
14 years 9 months ago
Latent semantic analysis
A new method for automatic indexing and retrieval is described. The approach is to take advantage of implicit higher-order structure in the association of terms with documents (&q...
Thomas K. Landauer, Susan T. Dumais
AINA
2010
IEEE
14 years 9 months ago
Compensation of Sensors Nonlinearity with Neural Networks
—This paper describes a method of linearizing the nonlinear characteristics of many sensors using an embedded neural network. The proposed method allows for complex neural networ...
Nicholas J. Cotton, Bogdan M. Wilamowski