In the framework of nonlinear process modeling, we propose training algorithms for feedback wavelet networks used as nonlinear dynamic models. An original initialization procedure...
— Recursive Neural Networks (RNNs) and Graph Neural Networks (GNNs) are two connectionist models that can directly process graphs. RNNs and GNNs exploit a similar processing fram...
Vincenzo Di Massa, Gabriele Monfardini, Lorenzo Sa...
A method to extract a fuzzy rule based system from a trained artificial neural network for classification is presented. The fuzzy system obtained is equivalent to the correspondin...
Abstract. One of the main problems associated with arti cial neural networks online learning methods is the estimation of model order. In this paper, we report about a new approach...
A new scalable optical network infrastructure SMART is proposed based on light-trails and hypernetwork architecture. The underlying physical network of SMART is a reconfigurable WD...