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...
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...
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...
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...
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...
: 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...