Matches in SemOpenAlex for { <https://semopenalex.org/work/W1991448507> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W1991448507 endingPage "32" @default.
- W1991448507 startingPage "23" @default.
- W1991448507 abstract "Node-perturbation learning (NP-learning) is a kind of statistical gradient descent algorithm that estimates the gradient of an objective function through application of a small perturbation to the outputs of the network. It can be applied to problems where the objective function is not explicitly formulated, including reinforcement learning. In this paper, we show that node-perturbation learning can be formulated as on-line learning in a linear perceptron with noise, and we can derive the differential equations of order parameters and the generalization error in the same way as for the analysis of learning in a linear perceptron through statistical mechanical methods. From analytical results, we show that cross-talk noise, which originates in the error of the other outputs, increases the generalization error as the output number increases." @default.
- W1991448507 created "2016-06-24" @default.
- W1991448507 creator A5015691007 @default.
- W1991448507 creator A5022010317 @default.
- W1991448507 creator A5033816900 @default.
- W1991448507 creator A5066486693 @default.
- W1991448507 date "2011-01-01" @default.
- W1991448507 modified "2023-10-05" @default.
- W1991448507 title "Statistical Mechanics of On-line Node-perturbation Learning" @default.
- W1991448507 cites W1964862779 @default.
- W1991448507 cites W1989730800 @default.
- W1991448507 cites W1995185910 @default.
- W1991448507 cites W2006598597 @default.
- W1991448507 cites W2035010839 @default.
- W1991448507 cites W2041176801 @default.
- W1991448507 cites W2065406692 @default.
- W1991448507 cites W2106437793 @default.
- W1991448507 cites W2116424792 @default.
- W1991448507 cites W2119717200 @default.
- W1991448507 cites W2145720061 @default.
- W1991448507 cites W2162160137 @default.
- W1991448507 cites W3141350557 @default.
- W1991448507 doi "https://doi.org/10.2197/ipsjtrans.4.23" @default.
- W1991448507 hasPublicationYear "2011" @default.
- W1991448507 type Work @default.
- W1991448507 sameAs 1991448507 @default.
- W1991448507 citedByCount "3" @default.
- W1991448507 countsByYear W19914485072013 @default.
- W1991448507 countsByYear W19914485072017 @default.
- W1991448507 crossrefType "journal-article" @default.
- W1991448507 hasAuthorship W1991448507A5015691007 @default.
- W1991448507 hasAuthorship W1991448507A5022010317 @default.
- W1991448507 hasAuthorship W1991448507A5033816900 @default.
- W1991448507 hasAuthorship W1991448507A5066486693 @default.
- W1991448507 hasBestOaLocation W19914485071 @default.
- W1991448507 hasConcept C11413529 @default.
- W1991448507 hasConcept C121332964 @default.
- W1991448507 hasConcept C121864883 @default.
- W1991448507 hasConcept C134306372 @default.
- W1991448507 hasConcept C153258448 @default.
- W1991448507 hasConcept C154945302 @default.
- W1991448507 hasConcept C177148314 @default.
- W1991448507 hasConcept C177918212 @default.
- W1991448507 hasConcept C179717631 @default.
- W1991448507 hasConcept C28826006 @default.
- W1991448507 hasConcept C33923547 @default.
- W1991448507 hasConcept C41008148 @default.
- W1991448507 hasConcept C50644808 @default.
- W1991448507 hasConcept C60908668 @default.
- W1991448507 hasConcept C62520636 @default.
- W1991448507 hasConcept C97541855 @default.
- W1991448507 hasConcept C99874945 @default.
- W1991448507 hasConceptScore W1991448507C11413529 @default.
- W1991448507 hasConceptScore W1991448507C121332964 @default.
- W1991448507 hasConceptScore W1991448507C121864883 @default.
- W1991448507 hasConceptScore W1991448507C134306372 @default.
- W1991448507 hasConceptScore W1991448507C153258448 @default.
- W1991448507 hasConceptScore W1991448507C154945302 @default.
- W1991448507 hasConceptScore W1991448507C177148314 @default.
- W1991448507 hasConceptScore W1991448507C177918212 @default.
- W1991448507 hasConceptScore W1991448507C179717631 @default.
- W1991448507 hasConceptScore W1991448507C28826006 @default.
- W1991448507 hasConceptScore W1991448507C33923547 @default.
- W1991448507 hasConceptScore W1991448507C41008148 @default.
- W1991448507 hasConceptScore W1991448507C50644808 @default.
- W1991448507 hasConceptScore W1991448507C60908668 @default.
- W1991448507 hasConceptScore W1991448507C62520636 @default.
- W1991448507 hasConceptScore W1991448507C97541855 @default.
- W1991448507 hasConceptScore W1991448507C99874945 @default.
- W1991448507 hasLocation W19914485071 @default.
- W1991448507 hasOpenAccess W1991448507 @default.
- W1991448507 hasPrimaryLocation W19914485071 @default.
- W1991448507 hasRelatedWork W1984869825 @default.
- W1991448507 hasRelatedWork W2007655795 @default.
- W1991448507 hasRelatedWork W2045559007 @default.
- W1991448507 hasRelatedWork W2074781637 @default.
- W1991448507 hasRelatedWork W2082247780 @default.
- W1991448507 hasRelatedWork W2100650658 @default.
- W1991448507 hasRelatedWork W2137656055 @default.
- W1991448507 hasRelatedWork W2296958142 @default.
- W1991448507 hasRelatedWork W2534897335 @default.
- W1991448507 hasRelatedWork W2614590078 @default.
- W1991448507 hasRelatedWork W2619720448 @default.
- W1991448507 hasRelatedWork W2791638061 @default.
- W1991448507 hasRelatedWork W2885971921 @default.
- W1991448507 hasRelatedWork W2895995061 @default.
- W1991448507 hasRelatedWork W2949181565 @default.
- W1991448507 hasRelatedWork W2949753371 @default.
- W1991448507 hasRelatedWork W2964299673 @default.
- W1991448507 hasRelatedWork W3016211582 @default.
- W1991448507 hasRelatedWork W3035719979 @default.
- W1991448507 hasRelatedWork W3130927411 @default.
- W1991448507 hasVolume "4" @default.
- W1991448507 isParatext "false" @default.
- W1991448507 isRetracted "false" @default.
- W1991448507 magId "1991448507" @default.
- W1991448507 workType "article" @default.