๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Neural network explanation using inversion

โœ Scribed by Emad W. Saad; Donald C. Wunsch II


Publisher
Elsevier Science
Year
2007
Tongue
English
Weight
869 KB
Volume
20
Category
Article
ISSN
0893-6080

No coin nor oath required. For personal study only.


๐Ÿ“œ SIMILAR VOLUMES


Safety-critical neural computing: explan
โœ J.H. Johnson; P.D. Picton; N.J. Hallam ๐Ÿ“‚ Article ๐Ÿ“… 1993 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 601 KB

This paper addresses the problem that conventional neural networks cannot contain a priori knowledge and cannot explain their output. A mathematical theory of 'black-box classifiers' is developed which covers most of the best known neural architectures. The limitations of the non-model based computa