Sciweavers

2960 search results - page 387 / 592
» Learning from Multiple Sources
Sort
View
ICCV
2007
IEEE
15 years 10 months ago
Support Kernel Machines for Object Recognition
Kernel classifiers based on Support Vector Machines (SVM) have recently achieved state-of-the art results on several popular datasets like Caltech or Pascal. This was possible by...
Ankita Kumar, Cristian Sminchisescu
IROS
2006
IEEE
233views Robotics» more  IROS 2006»
15 years 9 months ago
Machine-mediated Motor Skill Training Method in Haptic-enabled Chinese Handwriting Simulation System
Training of motor skill through machine-mediated method is a promising way to improve complex dexterous manipulation skill. New method of fusion between human motor skill and machi...
Dangxiao Wang, Yuru Zhang, Chong Yao
GECCO
2005
Springer
153views Optimization» more  GECCO 2005»
15 years 9 months ago
Evolving neural network ensembles for control problems
In neuroevolution, a genetic algorithm is used to evolve a neural network to perform a particular task. The standard approach is to evolve a population over a number of generation...
David Pardoe, Michael S. Ryoo, Risto Miikkulainen
GECCO
2005
Springer
204views Optimization» more  GECCO 2005»
15 years 9 months ago
Modeling systems with internal state using evolino
Existing Recurrent Neural Networks (RNNs) are limited in their ability to model dynamical systems with nonlinearities and hidden internal states. Here we use our general framework...
Daan Wierstra, Faustino J. Gomez, Jürgen Schm...
STOC
1997
ACM
97views Algorithms» more  STOC 1997»
15 years 8 months ago
Using and Combining Predictors That Specialize
Abstract. We study online learning algorithms that predict by combining the predictions of several subordinate prediction algorithms, sometimes called “experts.” These simple a...
Yoav Freund, Robert E. Schapire, Yoram Singer, Man...