The optimal design methodologies in aeronautics are known to be constrained by the computational burden required direct simulations. Due this reason, development of efficient metamodelling techniques represents nowadays an imperative need for designers. In fact, surrogate models has been demonstrated significantly reduce number high-fidelity evaluations, thus alleviating computing effort. Over ...

This paper will show that a new neural network design can solve an example of difficult function approximation problems which are crucial to the field of approximate dynamic programming(ADP). Although conventional neural networks have been proven to approximate smooth functions very well, the use of ADP for problems of intelligent control or planning requires the approximation of functions whic...

Echo state neural networks, which are a special case of recurrent neural networks, are studied from the viewpoint of their learning ability, with a goal to achieve their greater prediction ability. A standard training of these neural networks uses pseudoinverse matrix for one-step learning of weights from hidden to output neurons. This regular adaptation of Echo State neural networks was optimi...

Absbaet-In this note, the approximation capability of a class of discrete-time dynamic locurrent neural networks @RN"s) is studied. Analytieal lpsufts presented show that some of the states of sucb a D R " described by a set of dMerence equatbms may be used to approximate uniformly a ate-space trqjectmy pradufed by either a dismte-time nonlinear system or a cont i" fhnctkon on a closed disente-...

Transmission across neocortical synapses depends on the frequency of presynaptic activity (Thomson & Deuchars, 1994). Interpyramidal synapses in layer V exhibit fast depression of synaptic transmission, while other types of synapses exhibit facilitation of transmission. To study the role of dynamic synapses in network computation, we propose a unified phenomenological model that allows computat...