Sciweavers

IJON
2008
152views more  IJON 2008»
13 years 10 months ago
Topos: Spiking neural networks for temporal pattern recognition in complex real sounds
This article depicts the approach used to build the Topos application, a simulation of two-wheel robots able to discern real complex sounds. Topos is framed in the nouvelle concep...
Pablo González-Nalda, Blanca Cases
IJON
2008
133views more  IJON 2008»
13 years 10 months ago
A multi-objective approach to RBF network learning
The problem of inductive supervised learning is discussed in this paper within the context of multi-objective (MOBJ) optimization. The smoothness-based apparent (effective) comple...
Illya Kokshenev, Antônio de Pádua Bra...
IJON
2008
105views more  IJON 2008»
13 years 10 months ago
Estimating the number of components in a mixture of multilayer perceptrons
BIC criterion is widely used by the neural-network community for model selection tasks, although its convergence properties are not always theoretically established. In this paper...
Madalina Olteanu, Joseph Rynkiewicz
IJON
2008
124views more  IJON 2008»
13 years 11 months ago
A dynamic algorithm for blind separation of convolutive sound mixtures
We study an efficient dynamic blind source separation algorithm of convolutive sound mixtures based on updating statistical information in the frequency domain, and minimizing the...
Jie Liu, Jack Xin, Yingyong Qi
IJON
2008
156views more  IJON 2008»
13 years 11 months ago
Structural identifiability of generalized constraint neural network models for nonlinear regression
Identifiability becomes an essential requirement for learning machines when the models contain physically interpretable parameters. This paper presents two approaches to examining...
Shuang-Hong Yang, Bao-Gang Hu, Paul-Henry Courn&eg...
IJON
2008
116views more  IJON 2008»
13 years 11 months ago
Discovering speech phones using convolutive non-negative matrix factorisation with a sparseness constraint
Discovering a representation that allows auditory data to be parsimoniously represented is useful for many machine learning and signal processing tasks. Such a representation can ...
Paul D. O'Grady, Barak A. Pearlmutter
IJON
2008
88views more  IJON 2008»
13 years 11 months ago
Neural network construction and training using grammatical evolution
The term neural network evolution usually refers to network topology evolution leaving the network's parameters to be trained using conventional algorithms. In this paper we ...
Ioannis G. Tsoulos, Dimitris Gavrilis, Euripidis G...
IJON
2008
84views more  IJON 2008»
13 years 11 months ago
Prediction error of a fault tolerant neural network
John Sum, Andrew Chi-Sing Leung