Sciweavers

2924 search results - page 195 / 585
» On the Use of Evidence in Neural Networks
Sort
View
NN
1998
Springer
15 years 1 months ago
Statistical estimation of the number of hidden units for feedforward neural networks
The number of required hidden units is statistically estimated for feedforward neural networks that are constructed by adding hidden units one by one. The output error decreases w...
Osamu Fujita
SMC
2010
IEEE
276views Control Systems» more  SMC 2010»
15 years 10 days ago
A Modified Invasive Weed Optimization Algorithm for training of feed- forward Neural Networks
— Invasive Weed Optimization Algorithm IWO) is an ecologically inspired metaheuristic that mimics the process of weeds colonization and distribution and is capable of solving mul...
Ritwik Giri, Aritra Chowdhury, Arnob Ghosh, Swagat...
SIAMADS
2010
145views more  SIAMADS 2010»
14 years 8 months ago
Propagation of Spike Sequences in Neural Networks
Precise spatiotemporal sequences of action potentials are observed in many brain areas and are thought to be involved in the neural processing of sensory stimuli. Here, we examine ...
Arnaud Tonnelier
ICASSP
2011
IEEE
14 years 5 months ago
Deep neural networks for acoustic emotion recognition: Raising the benchmarks
Deep Neural Networks (DNNs) denote multilayer artificial neural networks with more than one hidden layer and millions of free parameters. We propose a Generalized Discriminant An...
André Stuhlsatz, Christine Meyer, Florian E...
ESANN
2008
15 years 3 months ago
Petri nets design based on neural networks
Petri net faulty models are useful for reliability analysis and fault diagnosis of discrete event systems. Such models are difficult to work out as long as they must be computed ac...
Edouard Leclercq, Souleiman Ould el Medhi, Dimitri...