The other variant Boltzmann machine
Resource
Neural Networks, 1989. IJCNN., International Joint Conference on
Journal
Neural Networks, 1989. IJCNN., International Joint Conference on
Pages
-
Date Issued
1989-06
Date
1989-06
Author(s)
Liou, Cheng-Yua
Lin, shiao-Li
DOI
N/A
Abstract
A novel theory for studying the learning behavior of a neural network which is formed by interconnecting neurons is presented. This learning theory constitutes a new approach to the Boltzmann machine. The central idea is to minimize one of the two cross-entropy-like criteria, the cross-entropy and the reversed cross-entropy; the latter is used by Ackley et al. (Cognitive Sci., vol.9, p.147-59, 1985) in deriving the Boltzmann machine. The results derived by the present approach are closely related to those obtained by Ackley et al., with several significant modifications in the algorithm. A detailed discussion of the new algorithm, which is shown to be a probability-weighted version of the algorithm by Ackley et al., is presented.>
Type
journal article
File(s)![Thumbnail Image]()
Loading...
Name
00118618.pdf
Size
391.33 KB
Format
Adobe PDF
Checksum
(MD5):ad7f500fbcc67bde82e133d5c9592666