Sciweavers

796 search results - page 45 / 160
» Plug-in Approach to Active Learning
Sort
View
ICPR
2010
IEEE
13 years 9 months ago
Scene-Adaptive Human Detection with Incremental Active Learning
In many computer vision tasks, scene changes hinder the generalization ability of trained classifiers. For instance, a human detector trained with one set of images is unlikely t...
Ajay Joshi, Fatih Porikli
ICANN
2003
Springer
14 years 3 months ago
Optimal Hebbian Learning: A Probabilistic Point of View
Many activity dependent learning rules have been proposed in order to model long-term potentiation (LTP). Our aim is to derive a spike time dependent learning rule from a probabili...
Jean-Pascal Pfister, David Barber, Wulfram Gerstne...
GECCO
2009
Springer
204views Optimization» more  GECCO 2009»
14 years 2 months ago
Combined structure and motion extraction from visual data using evolutionary active learning
We present a novel stereo vision modeling framework that generates approximate, yet physically-plausible representations of objects rather than creating accurate models that are c...
Krishnanand N. Kaipa, Josh C. Bongard, Andrew N. M...
BC
2006
105views more  BC 2006»
13 years 10 months ago
A stochastic population approach to the problem of stable recruitment hierarchies in spiking neural networks
Recruitment learning in hierarchies is an inherently unstable process (Valiant, 1994). This paper presents conditions on parameters for a feedforward network to ensure stable recru...
Cengiz Günay, Anthony S. Maida
ICML
2006
IEEE
14 years 11 months ago
Active sampling for detecting irrelevant features
The general approach for automatically driving data collection using information from previously acquired data is called active learning. Traditional active learning addresses the...
Sriharsha Veeramachaneni, Emanuele Olivetti, Paolo...