Matches in SemOpenAlex for { <https://semopenalex.org/work/W2597403208> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2597403208 endingPage "71" @default.
- W2597403208 startingPage "56" @default.
- W2597403208 abstract "The present paper aims to propose a simple method to realize mutual information maximization for better interpretation and generalization. To train neural networks and obtain better performance, neurons should impartially consider as many input patterns as possible. Simultaneously, and especially for ease of interpretation, they should represent characteristics specific to certain input patterns as faithfully as possible. This contradiction can be solved by introducing mutual information between neurons and input patterns. However, because of the complicated computational procedures associated with mutual information maximization, it has been difficult to apply mutual information maximization to actual problems. Though many simplified methods have been developed so far, they have not necessarily been applied with success, in particular to large-scale practical problems. To further aid simplification, here we propose a new computational method to realize mutual information. One of the main characteristics of this new method is the consideration of multiple neural networks when defining mutual information, thereby simplifying the method. In addition, learning is also simplified by using the indirect, independent, and fast learning of the potential method. This method was applied to two well known data sets: the Australian credit data and on-line popularity data set. The experimental results showed that mutual information could be increased via the present method. In addition, mutual information maximization was accompanied by an increase in generalization and interpretation performance, mainly due to the simple internal representations." @default.
- W2597403208 created "2017-03-23" @default.
- W2597403208 creator A5079603834 @default.
- W2597403208 date "2017-06-01" @default.
- W2597403208 modified "2023-09-23" @default.
- W2597403208 title "Collective mutual information maximization to unify passive and positive approaches for improving interpretation and generalization" @default.
- W2597403208 cites W1979191599 @default.
- W2597403208 cites W1986178142 @default.
- W2597403208 cites W2088736299 @default.
- W2597403208 cites W2105464873 @default.
- W2597403208 cites W2122925692 @default.
- W2597403208 cites W2123806929 @default.
- W2597403208 cites W2128420091 @default.
- W2597403208 cites W2138245406 @default.
- W2597403208 cites W2144914634 @default.
- W2597403208 cites W4205213118 @default.
- W2597403208 doi "https://doi.org/10.1016/j.neunet.2017.03.001" @default.
- W2597403208 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/28388473" @default.
- W2597403208 hasPublicationYear "2017" @default.
- W2597403208 type Work @default.
- W2597403208 sameAs 2597403208 @default.
- W2597403208 citedByCount "4" @default.
- W2597403208 countsByYear W25974032082018 @default.
- W2597403208 countsByYear W25974032082019 @default.
- W2597403208 countsByYear W25974032082021 @default.
- W2597403208 crossrefType "journal-article" @default.
- W2597403208 hasAuthorship W2597403208A5079603834 @default.
- W2597403208 hasConcept C111472728 @default.
- W2597403208 hasConcept C119857082 @default.
- W2597403208 hasConcept C124101348 @default.
- W2597403208 hasConcept C126255220 @default.
- W2597403208 hasConcept C134306372 @default.
- W2597403208 hasConcept C138885662 @default.
- W2597403208 hasConcept C152139883 @default.
- W2597403208 hasConcept C154945302 @default.
- W2597403208 hasConcept C177148314 @default.
- W2597403208 hasConcept C177264268 @default.
- W2597403208 hasConcept C199360897 @default.
- W2597403208 hasConcept C2776330181 @default.
- W2597403208 hasConcept C2780586882 @default.
- W2597403208 hasConcept C33923547 @default.
- W2597403208 hasConcept C41008148 @default.
- W2597403208 hasConcept C527412718 @default.
- W2597403208 hasConcept C7797323 @default.
- W2597403208 hasConceptScore W2597403208C111472728 @default.
- W2597403208 hasConceptScore W2597403208C119857082 @default.
- W2597403208 hasConceptScore W2597403208C124101348 @default.
- W2597403208 hasConceptScore W2597403208C126255220 @default.
- W2597403208 hasConceptScore W2597403208C134306372 @default.
- W2597403208 hasConceptScore W2597403208C138885662 @default.
- W2597403208 hasConceptScore W2597403208C152139883 @default.
- W2597403208 hasConceptScore W2597403208C154945302 @default.
- W2597403208 hasConceptScore W2597403208C177148314 @default.
- W2597403208 hasConceptScore W2597403208C177264268 @default.
- W2597403208 hasConceptScore W2597403208C199360897 @default.
- W2597403208 hasConceptScore W2597403208C2776330181 @default.
- W2597403208 hasConceptScore W2597403208C2780586882 @default.
- W2597403208 hasConceptScore W2597403208C33923547 @default.
- W2597403208 hasConceptScore W2597403208C41008148 @default.
- W2597403208 hasConceptScore W2597403208C527412718 @default.
- W2597403208 hasConceptScore W2597403208C7797323 @default.
- W2597403208 hasFunder F4320334764 @default.
- W2597403208 hasLocation W25974032081 @default.
- W2597403208 hasLocation W25974032082 @default.
- W2597403208 hasOpenAccess W2597403208 @default.
- W2597403208 hasPrimaryLocation W25974032081 @default.
- W2597403208 hasRelatedWork W1566144976 @default.
- W2597403208 hasRelatedWork W1566319786 @default.
- W2597403208 hasRelatedWork W2241417046 @default.
- W2597403208 hasRelatedWork W2524689738 @default.
- W2597403208 hasRelatedWork W2597403208 @default.
- W2597403208 hasRelatedWork W2908598672 @default.
- W2597403208 hasRelatedWork W2989932438 @default.
- W2597403208 hasRelatedWork W3088168130 @default.
- W2597403208 hasRelatedWork W3201070945 @default.
- W2597403208 hasRelatedWork W4307206503 @default.
- W2597403208 hasVolume "90" @default.
- W2597403208 isParatext "false" @default.
- W2597403208 isRetracted "false" @default.
- W2597403208 magId "2597403208" @default.
- W2597403208 workType "article" @default.