Sciweavers

Share
4 search results - page 1 / 1
» Investigating whether hyperNEAT produces modular neural netw...
Sort
View
GECCO
2010
Springer
168views Optimization» more  GECCO 2010»
9 years 8 months ago
Investigating whether hyperNEAT produces modular neural networks
HyperNEAT represents a class of neuroevolutionary algorithms that captures some of the power of natural development with a ionally efficient high-level abstraction of development....
Jeff Clune, Benjamin E. Beckmann, Philip K. McKinl...
GECCO
2006
Springer
291views Optimization» more  GECCO 2006»
9 years 7 months ago
Modular thinking: evolving modular neural networks for visual guidance of agents
This paper investigates whether replacing non-modular artificial neural network brains of visual agents with modular brains improves their ability to solve difficult tasks, specif...
Ehud Schlessinger, Peter J. Bentley, R. Beau Lotto
ECAI
2010
Springer
9 years 5 months ago
Unsupervised Layer-Wise Model Selection in Deep Neural Networks
Abstract. Deep Neural Networks (DNN) propose a new and efficient ML architecture based on the layer-wise building of several representation layers. A critical issue for DNNs remain...
Ludovic Arnold, Hélène Paugam-Moisy,...
IPMU
2010
Springer
9 years 6 months ago
Using Uncertainty Information to Combine Soft Classifications
The classification of remote sensing images performed with different classifiers usually produces different results. The aim of this paper is to investigate whether the outputs of ...
Luisa M. S. Gonçalves, Cidália C. Fo...
books