An efficient training method for block-diagonal recurrent neural networks is proposed. The method modifies the RPROP algorithm, originally developed for static models, in order to...
Paris A. Mastorocostas, Dimitris N. Varsamis, Cons...
Abstract. Automatic pattern classifiers that allow for on-line incremental learning can adapt internal class models efficiently in response to new information without retraining fr...
Abstract. Mechanisms for adapting models, filters, regulators and so on to changing properties of a system are of fundamental importance in many modern identification, estimation...
The paper deals with the concept of relevance learning in learning vector quantization and classification. Recent machine learning approaches with the ability of metric adaptation...
Thomas Villmann, Frank-Michael Schleif, Barbara Ha...
— This paper presents a single-objective and a multiobjective stochastic optimization algorithms for global training of neural networks based on simulated annealing. The algorith...