Gradient descent learning algorithms may get stuck in local minima, thus making the learning suboptimal. In this paper, we focus attention on multilayered networks used as autoassociators and show some relationships with classical linear autoassociators. In addition, using the theoretical framework of our previous research, we derive a condition which is met at the end of the learning process and show that this condition has a very intriguing geometrical meaning in the pattern space.
Bianchini, M., P., F., Gori, M. (1995). Learning in Multilayered Networks Used as Autoassociators. IEEE TRANSACTIONS ON NEURAL NETWORKS, 6(2), 512-515 [10.1109/72.363492].
Learning in Multilayered Networks Used as Autoassociators
BIANCHINI, MONICA;GORI, MARCO
1995-01-01
Abstract
Gradient descent learning algorithms may get stuck in local minima, thus making the learning suboptimal. In this paper, we focus attention on multilayered networks used as autoassociators and show some relationships with classical linear autoassociators. In addition, using the theoretical framework of our previous research, we derive a condition which is met at the end of the learning process and show that this condition has a very intriguing geometrical meaning in the pattern space.
| File | Dimensione | Formato | |
|---|---|---|---|
|
AUASS-TNN.pdf
non disponibili
Tipologia:
Post-print
Licenza:
NON PUBBLICO - Accesso privato/ristretto
Dimensione
342.1 kB
Formato
Adobe PDF
|
342.1 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.
https://hdl.handle.net/11365/22194
Attenzione
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo