Murari, AVega, JMazon, DPatane, D.Vagliasindi, GArena, P.Martin, NigelMartin, N.F.Ratta, G.Caloone, V.JET-EFDA, .2015-12-130168-9002http://hdl.handle.net/1885/79506Original methods to extract equations directly from experimental signals are presented. These techniques have been applied first to the determination of scaling laws for the threshold between the L and H mode of confinement in Tokamaks. The required equations can be extracted from the weights of neural networks and the separating hyperplane of Support Vector Machines. More powerful tools are required for the identification of differential equations directly from the time series of the signals. To this end, recurrent neural networks have proved to be very effective to properly identify ordinary differential equations and have been applied to the coupling between sawteeth and ELMs.Keywords: L-H transition; Machine-learning; Regression; Sawteeth; Separating hyperplane; SVM; Couplings; Dynamical systems; Fusion reactors; Ordinary differential equations; Scaling laws; Support vector machines; Time series; Recurrent neural networks L-H transition; Recurrent neural networks; Regression; Scaling laws; SVM201010.1016/j.nima.2010.02.0802016-02-24