Matches in SemOpenAlex for { <https://semopenalex.org/work/W1728366162> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W1728366162 abstract "The authors propose a novel learning algorithm with weighted error function (WEF). They have reduced the necessary precision for the learning of multi-font alpha-numeric recognition to 10-bit fixed point precision using the WEF. The WEF raises the recognition accuracy by more than 25% when the precision of all operations (including multiplication and addition) and the precision of all data (including weights and backpropagation signals) are limited to 10-bit fixed point. This improves the feasibility of analog implementation and lessens the data width of digital implementation. The performance of the WEF is high even with a small number of hidden neurons. This enables the reduction of weight memory. Furthermore, the WEF accelerates the learning and thus refines the adaptability of backpropagation. >" @default.
- W1728366162 created "2016-06-24" @default.
- W1728366162 creator A5004535457 @default.
- W1728366162 creator A5024603090 @default.
- W1728366162 creator A5034217125 @default.
- W1728366162 creator A5055042741 @default.
- W1728366162 creator A5059948406 @default.
- W1728366162 date "2002-12-09" @default.
- W1728366162 modified "2023-09-24" @default.
- W1728366162 title "Reduction of necessary precision for the learning of pattern recognition" @default.
- W1728366162 cites W1921777159 @default.
- W1728366162 cites W1971735090 @default.
- W1728366162 cites W2021641789 @default.
- W1728366162 cites W2043688814 @default.
- W1728366162 doi "https://doi.org/10.1109/ijcnn.1991.170355" @default.
- W1728366162 hasPublicationYear "2002" @default.
- W1728366162 type Work @default.
- W1728366162 sameAs 1728366162 @default.
- W1728366162 citedByCount "1" @default.
- W1728366162 crossrefType "proceedings-article" @default.
- W1728366162 hasAuthorship W1728366162A5004535457 @default.
- W1728366162 hasAuthorship W1728366162A5024603090 @default.
- W1728366162 hasAuthorship W1728366162A5034217125 @default.
- W1728366162 hasAuthorship W1728366162A5055042741 @default.
- W1728366162 hasAuthorship W1728366162A5059948406 @default.
- W1728366162 hasConcept C111335779 @default.
- W1728366162 hasConcept C11413529 @default.
- W1728366162 hasConcept C114614502 @default.
- W1728366162 hasConcept C153180895 @default.
- W1728366162 hasConcept C154945302 @default.
- W1728366162 hasConcept C155032097 @default.
- W1728366162 hasConcept C177606310 @default.
- W1728366162 hasConcept C18903297 @default.
- W1728366162 hasConcept C2524010 @default.
- W1728366162 hasConcept C2780595030 @default.
- W1728366162 hasConcept C28719098 @default.
- W1728366162 hasConcept C33923547 @default.
- W1728366162 hasConcept C41008148 @default.
- W1728366162 hasConcept C50644808 @default.
- W1728366162 hasConcept C86803240 @default.
- W1728366162 hasConceptScore W1728366162C111335779 @default.
- W1728366162 hasConceptScore W1728366162C11413529 @default.
- W1728366162 hasConceptScore W1728366162C114614502 @default.
- W1728366162 hasConceptScore W1728366162C153180895 @default.
- W1728366162 hasConceptScore W1728366162C154945302 @default.
- W1728366162 hasConceptScore W1728366162C155032097 @default.
- W1728366162 hasConceptScore W1728366162C177606310 @default.
- W1728366162 hasConceptScore W1728366162C18903297 @default.
- W1728366162 hasConceptScore W1728366162C2524010 @default.
- W1728366162 hasConceptScore W1728366162C2780595030 @default.
- W1728366162 hasConceptScore W1728366162C28719098 @default.
- W1728366162 hasConceptScore W1728366162C33923547 @default.
- W1728366162 hasConceptScore W1728366162C41008148 @default.
- W1728366162 hasConceptScore W1728366162C50644808 @default.
- W1728366162 hasConceptScore W1728366162C86803240 @default.
- W1728366162 hasLocation W17283661621 @default.
- W1728366162 hasOpenAccess W1728366162 @default.
- W1728366162 hasPrimaryLocation W17283661621 @default.
- W1728366162 hasRelatedWork W1493707092 @default.
- W1728366162 hasRelatedWork W1537589894 @default.
- W1728366162 hasRelatedWork W1605005685 @default.
- W1728366162 hasRelatedWork W1781893344 @default.
- W1728366162 hasRelatedWork W1998546613 @default.
- W1728366162 hasRelatedWork W2018769829 @default.
- W1728366162 hasRelatedWork W2025429934 @default.
- W1728366162 hasRelatedWork W2027403964 @default.
- W1728366162 hasRelatedWork W2083216547 @default.
- W1728366162 hasRelatedWork W2114528597 @default.
- W1728366162 hasRelatedWork W2132885024 @default.
- W1728366162 hasRelatedWork W2141185698 @default.
- W1728366162 hasRelatedWork W2150690754 @default.
- W1728366162 hasRelatedWork W2155515137 @default.
- W1728366162 hasRelatedWork W2158825478 @default.
- W1728366162 hasRelatedWork W2323241548 @default.
- W1728366162 hasRelatedWork W2355835431 @default.
- W1728366162 hasRelatedWork W2752860440 @default.
- W1728366162 hasRelatedWork W2964089137 @default.
- W1728366162 hasRelatedWork W3186222744 @default.
- W1728366162 isParatext "false" @default.
- W1728366162 isRetracted "false" @default.
- W1728366162 magId "1728366162" @default.
- W1728366162 workType "article" @default.