http://www.cnr.it/ontology/cnr/individuo/prodotto/ID173708
Pattern recognition as a deterministic problem: An approach based on discrepancy (Contributo in atti di convegno)
- Type
- Label
- Pattern recognition as a deterministic problem: An approach based on discrepancy (Contributo in atti di convegno) (literal)
- Anno
- 2003-01-01T00:00:00+01:00 (literal)
- Alternative label
Cervellera C., Muselli M. (2003)
Pattern recognition as a deterministic problem: An approach based on discrepancy
in First IAPR-TC3 Workshop, Florence, Italy, September 2003
(literal)
- Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori
- Cervellera C., Muselli M. (literal)
- Pagina inizio
- Pagina fine
- Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#titoloVolume
- Artificial Neural Networks in Pattern Recognition (literal)
- Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni
- C. Cervellera: CNR-ISSIA, Genova, Italy
M. Muselli: CNR-IEIIT, Genova, Italy (literal)
- Titolo
- Pattern recognition as a deterministic problem: An approach based on discrepancy (literal)
- Abstract
- When the position of each input vector in the training
set is not fixed beforehand, a deterministic approach can
be adopted to face with the general problem of learning.
In particular, the consistency of the Empirical Risk Minimization (ERM) principle can be established, when the
points in the input space are generated through a purely
deterministic algorithm (deterministic learning).
When the output generation is not subject to noise,
classical number-theoretic results, involving discrepancy
and variation, allow to establish a sufficient condition
for the consistency of the ERM principle. In addition,
the adoption of low-discrepancy sequences permits to
achieve a learning rate of O(1=L), being L the size of
the training set. (literal)
- Prodotto di
- Autore CNR
Incoming links:
- Prodotto
- Autore CNR di