Matches in SemOpenAlex for { <https://semopenalex.org/work/W2139463648> ?p ?o ?g. }
- W2139463648 abstract "In order to find an appropriate architecture for a large-scale real-world application automatically and efficiently, a natural method is to divide the original problem into a set of subproblems. In this paper, we propose a simple neural-network task decomposition method based on output parallelism. By using this method, a problem can be divided flexibly into several subproblems as chosen, each of which is composed of the whole input vector and a fraction of the output vector. Each module (for one subproblem) is responsible for producing a fraction of the output vector of the original problem. The hidden structure for the original problem's output units are decoupled. These modules can be grown and trained in parallel on parallel processing elements. Incorporated with a constructive learning algorithm, our method does not require excessive computation and any prior knowledge concerning decomposition. The feasibility of output parallelism is analyzed and proved. Some benchmarks are implemented to test the validity of this method. Their results show that this method can reduce computational time, increase learning speed and improve generalization accuracy for both classification and regression problems." @default.
- W2139463648 created "2016-06-24" @default.
- W2139463648 creator A5040285612 @default.
- W2139463648 creator A5065827089 @default.
- W2139463648 date "2002-05-01" @default.
- W2139463648 modified "2023-09-23" @default.
- W2139463648 title "Parallel growing and training of neural networks using output parallelism" @default.
- W2139463648 cites W1482651362 @default.
- W2139463648 cites W1570984485 @default.
- W2139463648 cites W1582499018 @default.
- W2139463648 cites W1962900642 @default.
- W2139463648 cites W196871588 @default.
- W2139463648 cites W1974985590 @default.
- W2139463648 cites W1996035835 @default.
- W2139463648 cites W2025653905 @default.
- W2139463648 cites W2042481239 @default.
- W2139463648 cites W2046789063 @default.
- W2139463648 cites W2051668038 @default.
- W2139463648 cites W2078422577 @default.
- W2139463648 cites W2086472796 @default.
- W2139463648 cites W2100283156 @default.
- W2139463648 cites W2109779438 @default.
- W2139463648 cites W2117955612 @default.
- W2139463648 cites W2133640977 @default.
- W2139463648 cites W2134631822 @default.
- W2139463648 cites W2142544077 @default.
- W2139463648 cites W2143908786 @default.
- W2139463648 cites W2145085734 @default.
- W2139463648 cites W2146615496 @default.
- W2139463648 cites W2150884987 @default.
- W2139463648 cites W2153382583 @default.
- W2139463648 cites W2160003106 @default.
- W2139463648 cites W2165758113 @default.
- W2139463648 cites W2467285039 @default.
- W2139463648 cites W2540560355 @default.
- W2139463648 cites W2766736793 @default.
- W2139463648 doi "https://doi.org/10.1109/tnn.2002.1000123" @default.
- W2139463648 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/18244455" @default.
- W2139463648 hasPublicationYear "2002" @default.
- W2139463648 type Work @default.
- W2139463648 sameAs 2139463648 @default.
- W2139463648 citedByCount "47" @default.
- W2139463648 countsByYear W21394636482012 @default.
- W2139463648 countsByYear W21394636482013 @default.
- W2139463648 countsByYear W21394636482014 @default.
- W2139463648 countsByYear W21394636482015 @default.
- W2139463648 countsByYear W21394636482016 @default.
- W2139463648 countsByYear W21394636482019 @default.
- W2139463648 crossrefType "journal-article" @default.
- W2139463648 hasAuthorship W2139463648A5040285612 @default.
- W2139463648 hasAuthorship W2139463648A5065827089 @default.
- W2139463648 hasBestOaLocation W21394636482 @default.
- W2139463648 hasConcept C106515295 @default.
- W2139463648 hasConcept C111919701 @default.
- W2139463648 hasConcept C11413529 @default.
- W2139463648 hasConcept C134306372 @default.
- W2139463648 hasConcept C149629883 @default.
- W2139463648 hasConcept C154945302 @default.
- W2139463648 hasConcept C173608175 @default.
- W2139463648 hasConcept C177148314 @default.
- W2139463648 hasConcept C177264268 @default.
- W2139463648 hasConcept C178790620 @default.
- W2139463648 hasConcept C185592680 @default.
- W2139463648 hasConcept C199360897 @default.
- W2139463648 hasConcept C2778701210 @default.
- W2139463648 hasConcept C2781172179 @default.
- W2139463648 hasConcept C33923547 @default.
- W2139463648 hasConcept C41008148 @default.
- W2139463648 hasConcept C45374587 @default.
- W2139463648 hasConcept C50644808 @default.
- W2139463648 hasConcept C98045186 @default.
- W2139463648 hasConceptScore W2139463648C106515295 @default.
- W2139463648 hasConceptScore W2139463648C111919701 @default.
- W2139463648 hasConceptScore W2139463648C11413529 @default.
- W2139463648 hasConceptScore W2139463648C134306372 @default.
- W2139463648 hasConceptScore W2139463648C149629883 @default.
- W2139463648 hasConceptScore W2139463648C154945302 @default.
- W2139463648 hasConceptScore W2139463648C173608175 @default.
- W2139463648 hasConceptScore W2139463648C177148314 @default.
- W2139463648 hasConceptScore W2139463648C177264268 @default.
- W2139463648 hasConceptScore W2139463648C178790620 @default.
- W2139463648 hasConceptScore W2139463648C185592680 @default.
- W2139463648 hasConceptScore W2139463648C199360897 @default.
- W2139463648 hasConceptScore W2139463648C2778701210 @default.
- W2139463648 hasConceptScore W2139463648C2781172179 @default.
- W2139463648 hasConceptScore W2139463648C33923547 @default.
- W2139463648 hasConceptScore W2139463648C41008148 @default.
- W2139463648 hasConceptScore W2139463648C45374587 @default.
- W2139463648 hasConceptScore W2139463648C50644808 @default.
- W2139463648 hasConceptScore W2139463648C98045186 @default.
- W2139463648 hasLocation W21394636481 @default.
- W2139463648 hasLocation W21394636482 @default.
- W2139463648 hasLocation W21394636483 @default.
- W2139463648 hasOpenAccess W2139463648 @default.
- W2139463648 hasPrimaryLocation W21394636481 @default.
- W2139463648 hasRelatedWork W1507480455 @default.
- W2139463648 hasRelatedWork W2000923966 @default.
- W2139463648 hasRelatedWork W200799616 @default.
- W2139463648 hasRelatedWork W2009603406 @default.
- W2139463648 hasRelatedWork W2010783912 @default.