Matches in SemOpenAlex for { <https://semopenalex.org/work/W2040408794> ?p ?o ?g. }
Showing items 1 to 58 of
58
with 100 items per page.
- W2040408794 abstract "The notion of multiversion system design is imported from software engineering where it has sometimes been used as part of a strategy for producing highly reliable software. We have further developed and refined this notion such that we can confidently undertake to improve the performance of any single neural network. For a number of reasons neural computing is better suited for use with a multiversion strategy than the conventional computing from whence the basic idea came. We have developed a methodology to underpin a multiversion approach to highly reliable neural net implementations. We present this methodology and several different applications of it (e.g., single level and two-level multiversion systems) that demonstrate the generalisation improvements obtainable within the general framework of a diverse, multiversion approach. A variety of results are compared and contrasted. They indicate that significant generalisation improvements can be obtained by a variety of different means." @default.
- W2040408794 created "2016-06-24" @default.
- W2040408794 creator A5008608009 @default.
- W2040408794 creator A5046288765 @default.
- W2040408794 date "1995-01-01" @default.
- W2040408794 modified "2023-09-22" @default.
- W2040408794 title "Engineering reliable neural networks" @default.
- W2040408794 doi "https://doi.org/10.1049/cp:19950581" @default.
- W2040408794 hasPublicationYear "1995" @default.
- W2040408794 type Work @default.
- W2040408794 sameAs 2040408794 @default.
- W2040408794 citedByCount "3" @default.
- W2040408794 crossrefType "proceedings-article" @default.
- W2040408794 hasAuthorship W2040408794A5008608009 @default.
- W2040408794 hasAuthorship W2040408794A5046288765 @default.
- W2040408794 hasConcept C115903868 @default.
- W2040408794 hasConcept C136197465 @default.
- W2040408794 hasConcept C154945302 @default.
- W2040408794 hasConcept C199360897 @default.
- W2040408794 hasConcept C26713055 @default.
- W2040408794 hasConcept C2777904410 @default.
- W2040408794 hasConcept C41008148 @default.
- W2040408794 hasConcept C50644808 @default.
- W2040408794 hasConceptScore W2040408794C115903868 @default.
- W2040408794 hasConceptScore W2040408794C136197465 @default.
- W2040408794 hasConceptScore W2040408794C154945302 @default.
- W2040408794 hasConceptScore W2040408794C199360897 @default.
- W2040408794 hasConceptScore W2040408794C26713055 @default.
- W2040408794 hasConceptScore W2040408794C2777904410 @default.
- W2040408794 hasConceptScore W2040408794C41008148 @default.
- W2040408794 hasConceptScore W2040408794C50644808 @default.
- W2040408794 hasLocation W20404087941 @default.
- W2040408794 hasOpenAccess W2040408794 @default.
- W2040408794 hasPrimaryLocation W20404087941 @default.
- W2040408794 hasRelatedWork W1853906130 @default.
- W2040408794 hasRelatedWork W1978071567 @default.
- W2040408794 hasRelatedWork W2103847506 @default.
- W2040408794 hasRelatedWork W2116608525 @default.
- W2040408794 hasRelatedWork W2124920252 @default.
- W2040408794 hasRelatedWork W2127563587 @default.
- W2040408794 hasRelatedWork W2135151593 @default.
- W2040408794 hasRelatedWork W2140362372 @default.
- W2040408794 hasRelatedWork W2143958548 @default.
- W2040408794 hasRelatedWork W2144595992 @default.
- W2040408794 hasRelatedWork W2152490675 @default.
- W2040408794 hasRelatedWork W2167955484 @default.
- W2040408794 hasRelatedWork W2168874580 @default.
- W2040408794 hasRelatedWork W2262620029 @default.
- W2040408794 hasRelatedWork W2293943698 @default.
- W2040408794 hasRelatedWork W2753751386 @default.
- W2040408794 hasRelatedWork W3008611995 @default.
- W2040408794 hasRelatedWork W3107571387 @default.
- W2040408794 hasRelatedWork W3129804067 @default.
- W2040408794 hasRelatedWork W3169822714 @default.
- W2040408794 isParatext "false" @default.
- W2040408794 isRetracted "false" @default.
- W2040408794 magId "2040408794" @default.
- W2040408794 workType "article" @default.