Deep neural networks and Multiple Kernel Learning are representation learning methodologies of widespread use and increasing success. While the former aims at learning representations through a hierarchy of features of increasing complexity, the latter provides a principled approach for the combination of base representations. In this paper, we introduce a general framework in which the internal representations computed by a deep neural network are optimally combined by means of Multiple Kernel Learning. The resulting ensemble methodology is instantiated for Multi-layer Perceptrons architectures (both fully trained and with random-weights), and for Convolutional Neural Networks. Experimental results on several benchmark datasets concretely show the advantages and potentialities of the proposed approach.
Enhancing deep neural networks via multiple kernel learning
Gallicchio C.;
2020-01-01
Abstract
Deep neural networks and Multiple Kernel Learning are representation learning methodologies of widespread use and increasing success. While the former aims at learning representations through a hierarchy of features of increasing complexity, the latter provides a principled approach for the combination of base representations. In this paper, we introduce a general framework in which the internal representations computed by a deep neural network are optimally combined by means of Multiple Kernel Learning. The resulting ensemble methodology is instantiated for Multi-layer Perceptrons architectures (both fully trained and with random-weights), and for Convolutional Neural Networks. Experimental results on several benchmark datasets concretely show the advantages and potentialities of the proposed approach.File | Dimensione | Formato | |
---|---|---|---|
kernet_postprint.pdf
Open Access dal 02/01/2022
Descrizione: post-print
Tipologia:
Documento in Post-print
Licenza:
Creative commons
Dimensione
4.25 MB
Formato
Adobe PDF
|
4.25 MB | Adobe PDF | Visualizza/Apri |
Enhancing deep neural networks.pdf
non disponibili
Tipologia:
Versione finale editoriale
Licenza:
NON PUBBLICO - accesso privato/ristretto
Dimensione
941.45 kB
Formato
Adobe PDF
|
941.45 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.