In the case of static data of high dimension it is often useful to reduce the dimensionality before performing pattern recognition and learning tasks. One of the main reasons for this is that models for lower-dimensional data usually have fewer parameters to be determined. The problem of finding fixed-length vector representations for labelled directed ordered acyclic graphs (DOAGs) can be regarded as a feature extraction problem in which the dimensionality of the input space is infinite. We address the fundamental problem of finding fixed-length vector representations for DOAGs in an unsupervised way using a maximum entropy approach. Some preliminary experiments on image retrieval are reported.

C., G., Gori, M., Maggini, M. (1999). Feature extraction from data structures with unsupervised recursive neural networks. In Proceedings of the International Joint Conference on Neural Networks 1999 (pp.1121-1126) [10.1109/IJCNN.1999.831114].

Feature extraction from data structures with unsupervised recursive neural networks

GORI, MARCO;MAGGINI, MARCO
1999-01-01

Abstract

In the case of static data of high dimension it is often useful to reduce the dimensionality before performing pattern recognition and learning tasks. One of the main reasons for this is that models for lower-dimensional data usually have fewer parameters to be determined. The problem of finding fixed-length vector representations for labelled directed ordered acyclic graphs (DOAGs) can be regarded as a feature extraction problem in which the dimensionality of the input space is infinite. We address the fundamental problem of finding fixed-length vector representations for DOAGs in an unsupervised way using a maximum entropy approach. Some preliminary experiments on image retrieval are reported.
1999
0780355296
C., G., Gori, M., Maggini, M. (1999). Feature extraction from data structures with unsupervised recursive neural networks. In Proceedings of the International Joint Conference on Neural Networks 1999 (pp.1121-1126) [10.1109/IJCNN.1999.831114].
File in questo prodotto:
File Dimensione Formato  
IJCNN99b.pdf

non disponibili

Tipologia: Post-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 538.56 kB
Formato Adobe PDF
538.56 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.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11365/35150
 Attenzione

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