Sciweavers

ESANN
1998
14 years 24 days ago
Speech recognition with a new hybrid architecture combining neural networks and continuous HMM
Abstract. In this paper, we focus on a novel NN/HMM architecture for continuous speech recognition. The architecture incorporates a neural feature extraction to gain more discrimin...
Daniel Willett, Gerhard Rigoll
ESANN
1998
14 years 24 days ago
Parsimonious learning feed-forward control
Theo J. A. de Vries, Lars J. Idema, Wubbe J. R. Ve...
ESANN
1998
14 years 24 days ago
A comparison between weighted radial basis functions and wavelet networks
In the present paper, Wavelet Networks, are proven to be, as well as many other neural paradigms, a speci c case of the generic paradigm named Weighted Radial Basis Functions Netw...
Mirko Sgarbi, Valentina Colla, Leonardo Maria Reyn...
ESANN
1998
14 years 24 days ago
A self-organising neural network for modelling cortical development
This paper presents a novel self-organising neural network. It has been developed for use as a simpli ed model of cortical development. Unlike many other models of topological map...
Michael W. Spratling, Gillian Hayes
ESANN
1998
14 years 24 days ago
Forecasting time-series by Kohonen classification
In this paper, we propose a generic non-linear approach for time series forecasting. The main feature of this approach is the use of a simple statistical forecasting in small regio...
Amaury Lendasse, Michel Verleysen, Eric de Bodt, M...
ESANN
1998
14 years 24 days ago
Recurrent SOM with local linear models in time series prediction
Recurrent Self-Organizing Map (RSOM) is studied in three di erent time series prediction cases. RSOM is used to cluster the series into local data sets, for which corresponding lo...
Timo Koskela, Markus Varsta, Jukka Heikkonen, Kimm...
ESANN
1998
14 years 24 days ago
NAR time-series prediction: a Bayesian framework and an experiment
: We extend the Bayesian framework to Multi-Layer Perceptron models of Non-linear Auto-Regressive time-series. The approach is evaluated on an artificial time-series and some commo...
Michel Crucianu, Crucianu Uhry, Jean Pierre Asseli...