Recently, deep networks were proved to be more effective than shallow architectures to face complex real–world applications. However, theoretical results supporting this claim are still few and incomplete. In this paper, we propose a new topological measure to study how the depth of feedforward networks impacts on their ability of implementing high complexity functions. Upper and lower bounds on network complexity are established, based on the number of hidden units and on their activation functions, showing that deep architectures are able, with the same number of resources, to address more difficult classification problems.

Bianchini, M., & Scarselli, F. (2014). On the complexity of shallow and deep neural network classifiers. In ESANN 2014 proceedings (pp.371-376). i6doc.com publication.

On the complexity of shallow and deep neural network classifiers

BIANCHINI, MONICA;SCARSELLI, FRANCO
2014

Abstract

Recently, deep networks were proved to be more effective than shallow architectures to face complex real–world applications. However, theoretical results supporting this claim are still few and incomplete. In this paper, we propose a new topological measure to study how the depth of feedforward networks impacts on their ability of implementing high complexity functions. Upper and lower bounds on network complexity are established, based on the number of hidden units and on their activation functions, showing that deep architectures are able, with the same number of resources, to address more difficult classification problems.
978-287419095-7
File in questo prodotto:
File Dimensione Formato  
es2014-44.pdf

non disponibili

Tipologia: PDF editoriale
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 1.57 MB
Formato Adobe PDF
1.57 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11365/875042
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo