A fuzzy backpropagation algorithm

Simple item page
dc.contributor.authorStoeva, Stefka
dc.contributor.authorNikov, Alexander
dc.date.accessioned2011-06-14T12:03:33Z
dc.date.available2011-06-14T12:03:33Z
dc.date.issued2011-06-14
dc.description.abstractThis paper presents an extension of the standard backpropagation algorithm (SBP). The proposed learning algorithm is based on the fuzzy integral of Sugeno and thus called fuzzy backpropagation (FBP) algorithm. Necessary and sufficient conditions for convergence of FBP algorithm for single-output networks in case of single- and multiple-training patterns are proved. A computer simulation illustrates and confirms the theoretical results. FBP algorithm shows considerably greater convergence rate compared to SBP algorithm. Other advantages of FBP algorithm are that it reaches forward to the target value without oscillations, requires no assumptions about probability distribution and independence of input data. The convergence conditions enable training by automation of weights tuning process (quasi-unsupervised learning) pointing out the interval where the target value belongs to. This supports acquisition of implicit knowledge and ensures wide application, e.g. for creation of adaptable user interfaces, assessment of products, intelligent data analysis, etc.en_US
dc.identifier.urihttps://hdl.handle.net/2139/10115
dc.language.isoenen_US
dc.subjectNeural networksen_US
dc.subjectLearning algorithmen_US
dc.subjectFuzzy logicen_US
dc.subjectMulticriteria analysisen_US
dc.titleA fuzzy backpropagation algorithmen_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
fuzzy.html
Size:
366 B
Format:
Hypertext Markup Language
Description:
A fuzzy backpropagation algorithm
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.78 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

DCIT Lecturers' Papers