The convex hull of any subset of vertices of an n-dimensional hypercube contains no other vertex of the hypercube. This result permits the application of some theorems of n-dimensional geometry to digital feed-forward neural networks. Also, the construction of the convex hull is proposed as an alternative to more traditional learning algorithms. Some preliminary simulation results are reported.
Feed-Forward Neural Networks: a Geometrical Perspective / Budinich, Marco; Milotti, Edoardo. - In: JOURNAL OF PHYSICS. A, MATHEMATICAL AND THEORETICAL. - ISSN 1751-8113. - STAMPA. - 1991:(1991), pp. 881-888. [10.1088/0305-4470/24/4/020]
Feed-Forward Neural Networks: a Geometrical Perspective
BUDINICH, MARCO;MILOTTI, EDOARDO
1991-01-01
Abstract
The convex hull of any subset of vertices of an n-dimensional hypercube contains no other vertex of the hypercube. This result permits the application of some theorems of n-dimensional geometry to digital feed-forward neural networks. Also, the construction of the convex hull is proposed as an alternative to more traditional learning algorithms. Some preliminary simulation results are reported.File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
