ESANN
2000
14 years 24 days 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
14 years 24 days 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
14 years 24 days 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
14 years 24 days 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
14 years 24 days 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
14 years 24 days ago
2000
ESANN
2000
14 years 24 days 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
14 years 24 days 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
14 years 24 days 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
14 years 24 days 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...