We show that under reasonable conditions, online learning for a nonlinear function near a local minimum is similar to a multivariate Ornstein Uhlenbeck process. This implies that ...
A Hybrid modeling approach, combining an analytical model with a radial basis function neural network is introduced in this paper. The modeling procedure is combined with genetic a...
Primoz Potocnik, Igor Grabec, Marko Setinc, Janez ...
This paper presents a novel self-creating neural network scheme which employs two resource counters to record network learning activity. The proposed scheme not only achieves the b...
The learning of complex relationships can be decomposed into several neural networks. The modular organization is determined by prior knowledge of the problem that permits to split...
The `kernel approach' has attracted great attention with the development of support vector machine (SVM) and has been studied in a general way. It offers an alternative soluti...