๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Network information criterion-determining the number of hidden units for an artificial neural network model

โœ Scribed by Murata, N.; Yoshizawa, S.; Amari, S.


Book ID
121814107
Publisher
IEEE
Year
1994
Tongue
English
Weight
723 KB
Volume
5
Category
Article
ISSN
1045-9227

No coin nor oath required. For personal study only.


๐Ÿ“œ SIMILAR VOLUMES


Statistical estimation of the number of
โœ Osamu Fujita ๐Ÿ“‚ Article ๐Ÿ“… 1998 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 273 KB

The number of required hidden units is statistically estimated for feedforward neural networks that are constructed by adding hidden units one by one. The output error decreases with the number of hidden units by an almost constant rate, if each appropriate hidden unit is selected out of a great num