Sciweavers

2924 search results - page 332 / 585
» On the Use of Evidence in Neural Networks
Sort
View
ESANN
2004
15 years 8 months ago
Online policy adaptation for ensemble classifiers
Ensemble algorithms can improve the performance of a given learning algorithm through the combination of multiple base classifiers into an ensemble. In this paper, the idea of usin...
Christos Dimitrakakis, Samy Bengio
NPL
1998
175views more  NPL 1998»
15 years 6 months ago
Prediction of Chaotic Time-Series with a Resource-Allocating RBF Network
Abstract. One of the main problems associated with arti cial neural networks online learning methods is the estimation of model order. In this paper, we report about a new approach...
Roman Rosipal, Milos Koska, Igor Farkas
IWANN
2007
Springer
16 years 24 days ago
Integration of Wind Sensors and Analogue VLSI for an Insect-Inspired Robot
We have designed an adaptive analogue VLSI neuromorphic chip that will be used to interface MEM wind sensors to an insectinspired robot. The main chip components are a sensory inte...
Y. Zhang, A. Hamilton, R. Cheung, B. Webb, P. Argy...
ICANN
2005
Springer
16 years 5 days ago
A Model for Delay Activity Without Recurrent Excitation
Delay activity (DA) is the increased firing rate of a cortical population, which persists when the stimulus that induced it is removed. It is believed to be the neural substrate f...
Marc de Kamps
ECAL
2003
Springer
15 years 12 months ago
First Steps in Evolving Path Integration in Simulation
Abstract. Path integration is a widely used method of navigation in nature whereby an animal continuously tracks its location by integrating its motion over the course of a journey...
Robert Vickerstaff