ESANN
2000
13 years 5 months ago
2000
Abstract. In this paper, we presen t an algorithm that provides adaptive plasticity in function approximation problems: the deformable (feature) map (DM) algorithm. The DM approach...
ESANN
2000
13 years 5 months ago
2000
The basic SOM is indi erent to the ordering of the input patterns. Real data, however, is often sequential in nature thus context of a pattern may signi cantly in uence its correc...
ESANN
2000
13 years 5 months ago
2000
Abstract. We present local conditions for input-output stability of recurrent neural networks with time-varying parameters introduced for instance by noise or on-line adaptation. T...
ESANN
2000
13 years 5 months ago
2000
In this paper we shortly discuss the K.U. Leuven time-series prediction competition, which has been held in the framework of the International Workshop on Advanced Black-Box Techni...
ESANN
2000
13 years 5 months ago
2000
The problem of model selection is considerably important for acquiring higher levels of generalization capability in supervised learning. In this paper, we propose a new criterion ...
ESANN
2000
13 years 5 months ago
2000
ESANN
2000
13 years 5 months ago
2000
Abstract. This paper proposes a mathematical programming framew ork for combining SVMs with possibly di erent kernels. Compared to single SVMs, the advantage of this approach is tw...
ESANN
2000
13 years 5 months ago
2000
A system for the automatic segmentation of fluorescence micrographs is presented. In a first step positions of fluorescent cells are detected by a fast learning neural network, whi...
ESANN
2000
13 years 5 months ago
2000
Abstract. A prediction scheme for spatio-temporal time series is presented that is based on reconstructed local states. As a numerical example the ev olution of a Kuramoto-Sivashin...
ESANN
2000
13 years 5 months ago
2000
Feed-forward neural networks (Multi-Layered Perceptrons) are used widely in real-world regression or classification tasks. A reliable and practical measure of prediction "conf...