Sciweavers

313 search results - page 3 / 63
» Consistent Approximations and Approximate Functions and Grad...
Sort
View
ISBI
2004
IEEE
14 years 6 months ago
Multi-Modal Non-Rigid Registration Using a Stochastic Gradient Approximation
We present a new fast implementation of a non-rigid registration algorithm, based on a finite element elastic deformation model using the mutual information metric with a linear e...
Aloys du Bois d'Aische, Benoît Macq, Florian...
ICML
2000
IEEE
14 years 6 months ago
Reinforcement Learning in POMDP's via Direct Gradient Ascent
This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled ??? ?s. We introduce ??? ?, a...
Jonathan Baxter, Peter L. Bartlett
ATAL
2005
Springer
13 years 11 months ago
Improving reinforcement learning function approximators via neuroevolution
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...
Shimon Whiteson
ICRA
2007
IEEE
171views Robotics» more  ICRA 2007»
13 years 11 months ago
Visual Servoing by Optimization of a 2D/3D Hybrid Objective Function
— In this paper, we present a new hybrid visual servoing algorithm for robot arm positioning task. Hybrid methods in visual servoing partially combine the 2D and 3D visual inform...
A. H. Abdul Hafez, C. V. Jawahar
IR
2010
13 years 3 months ago
Gradient descent optimization of smoothed information retrieval metrics
Abstract Most ranking algorithms are based on the optimization of some loss functions, such as the pairwise loss. However, these loss functions are often different from the criter...
Olivier Chapelle, Mingrui Wu