http://www.cnr.it/ontology/cnr/individuo/prodotto/ID260257
Is pocket algorithm optimal? (Articolo in rivista)
- Type
- Label
- Is pocket algorithm optimal? (Articolo in rivista) (literal)
- Anno
- 1995-01-01T00:00:00+01:00 (literal)
- Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#doi
- 10.1007/3-540-59119-2_185 (literal)
- Alternative label
- Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori
- Pagina inizio
- Pagina fine
- Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#numeroVolume
- Rivista
- Note
- Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni
- M. Muselli: CNR-IEIIT, Genova, Italy (literal)
- Titolo
- Is pocket algorithm optimal? (literal)
- Abstract
- Most learning algorithms for single neuron are not able to provide for any classification problem
the weight vector which satisfies the maximum number of input-output relations contained
in the training set. An important exception is given by the pocket algorithm: it repeatedly
executes the perceptron algorithm and maintains (in the pocket) the weight vector which is
remained unchanged for the highest number of iterations.
A proper convergence theorem ensures the achievement of an optimal configuration with
probability one when the number of iterations grows indefinitely. This theoretical result is used
for showing the good convergence properties of other learning methods for multilayered neural
networks, which employ pocket algorithm as a basic task.
In the present paper a new formulation of the pocket convergence theorem is given; a
rigorous proof corrects some formal and substantial errors which invalidate previous theoretical
results. In particular it is shown that the optimality of the asymptotical solution is ensured
only if the number of permanences for the pocket vector lies in a proper interval of the real
axis which bounds depend on the number of iterations. (literal)
- Prodotto di
- Autore CNR
Incoming links:
- Prodotto
- Autore CNR di
- Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#rivistaDi
