๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Error prediction for neural networks by fuzzification

โœ Scribed by Thomas Feuring; Wolfram-M. Lippe

Publisher
John Wiley and Sons
Year
1998
Tongue
English
Weight
105 KB
Volume
13
Category
Article
ISSN
0884-8173

No coin nor oath required. For personal study only.

โœฆ Synopsis

รn classical ''crisp'' neural networks the output cannot be estimated for arbitrary input data. This situation can be overcome if fuzzy neural nets are trained with fuzzy data. These ''continuous'' data often better describe certain situations. Because fuzzy neural networks map fuzzy numbers to fuzzy numbers, a criterion for choosing a ''good'' training set can be formulated. Together with an important fuzzy neural network property, the output for arbitrary crisp input data can be estimated based on the fuzzy training set.

๐Ÿ“œ SIMILAR VOLUMES

Probabilistic neural networks for seismi
Probabilistic neural networks for seismic damage mechanisms prediction
โœ De Stefano, A.; Sabia, D.; Sabia, L. ๐Ÿ“‚ Article ๐Ÿ“… 1999 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 198 KB ๐Ÿ‘ 1 views

The procedure commonly employed to assess the seismic vulnerability of buildings uses simpli"ed qualitative and quantitative observations obtained from the measured data entered into report forms. In Italy, the data sheets adopted by the National Defence Group against Earthquakes (Gruppo Nazionale p