On-line Backpropagation has become very popular and it has been the subject of in-depth theoretical analyses and massive experimentation. Yet, after almost three decades from its publication, it is still surprisingly the source of tough theoretical questions and of experimental results that are somewhat shrouded in mystery. Although seriously plagued by local minima, the batch-mode version of the algorithm is clearly posed as an optimization problem while, in spite of its effectiveness, in many real-world problems the on-line mode version has not been given a clean formulation, yet. Using variational arguments, in this paper, the on-line formulation is proposed as the minimization of a classic functional that is inspired by the principle of minimal action in analytic mechanics. The proposed approach clashes sharply with common interpretations of on-line learning as an approximation of batch-mode, and it suggests that processing data all at once might be just an artificial formulation of learning that is hopeless in difficult real-world problems. © 2013 Springer-Verlag Berlin Heidelberg.
|Data di pubblicazione:||2013|
|Titolo:||Variational foundations of online backpropagation|
|Autore/i:||Frandina, Salvatore; Gori, Marco; Lippi, Marco; Maggini, Marco; Melacci, Stefano|
|Digital Object Identifier (DOI):||10.1007/978-3-642-40728-4_11|
|Nome del convegno:||23rd International Conference on Artificial Neural Networks, ICANN 2013|
|Luogo del convegno:||Sofia, bgr|
|Data del convegno:||2013|
|Citazione:||Variational foundations of online backpropagation / Frandina, Salvatore; Gori, Marco; Lippi, Marco; Maggini, Marco; Melacci, Stefano. - 8131(2013), pp. 82-89. ((Intervento presentato al convegno 23rd International Conference on Artificial Neural Networks, ICANN 2013 tenutosi a Sofia, bgr nel 2013.|
|Tipologia||Relazione in Atti di Convegno|
I documenti presenti in Iris Unimore sono rilasciati con licenza Creative Commons Attribuzione - Non commerciale - Non opere derivate 3.0 Italia, salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris