FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2739741052> ?p ?o ?g. }

• W2739741052 endingPage "3298" @default.
• W2739741052 startingPage "3289" @default.
• W2739741052 abstract "Fisher information and natural gradient provided deep insights and powerful tools to artificial neural networks. However related analysis becomes more and more difficult as the learner's structure turns large and complex. This paper makes a preliminary step towards anew direction. We extract a local component from a large neural system, and define its relative Fisher information metric that describes accurately this small component, and is invariant to the other parts of the system. This concept is important because the geometry structure is much simplified and it can be easily applied to guide the learning of neural networks. We provide an analysis on a list of commonly used components, and demonstrate how to use this concept to further improve optimization." @default.
• W2739741052 created "2017-08-08" @default.
• W2739741052 creator A5061293973 @default.
• W2739741052 creator A5068048142 @default.
• W2739741052 date "2017-08-06" @default.
• W2739741052 modified "2023-09-23" @default.
• W2739741052 title "Relative fisher information and natural gradient for learning large modular models" @default.
• W2739741052 cites W1138777372 @default.
• W2739741052 cites W130339674 @default.
• W2739741052 cites W1522301498 @default.
• W2739741052 cites W1525296983 @default.
• W2739741052 cites W1556355936 @default.
• W2739741052 cites W1581755290 @default.
• W2739741052 cites W1583776211 @default.
• W2739741052 cites W1665214252 @default.
• W2739741052 cites W1677182931 @default.
• W2739741052 cites W1836465849 @default.
• W2739741052 cites W1871231525 @default.
• W2739741052 cites W1915968771 @default.
• W2739741052 cites W1959492 @default.
• W2739741052 cites W1959608418 @default.
• W2739741052 cites W196761320 @default.
• W2739741052 cites W1970789124 @default.
• W2739741052 cites W2015985330 @default.
• W2739741052 cites W2036632921 @default.
• W2739741052 cites W2038073775 @default.
• W2739741052 cites W2067342226 @default.
• W2739741052 cites W2097117768 @default.
• W2739741052 cites W2136739711 @default.
• W2739741052 cites W2136922672 @default.
• W2739741052 cites W2144647101 @default.
• W2739741052 cites W2149458751 @default.
• W2739741052 cites W2152424459 @default.
• W2739741052 cites W2155894447 @default.
• W2739741052 cites W2164273299 @default.
• W2739741052 cites W2167729035 @default.
• W2739741052 cites W2176412452 @default.
• W2739741052 cites W2292596728 @default.
• W2739741052 cites W2292751606 @default.
• W2739741052 cites W2396602259 @default.
• W2739741052 cites W2467681623 @default.
• W2739741052 cites W2485135680 @default.
• W2739741052 cites W2586850891 @default.
• W2739741052 cites W2619348793 @default.
• W2739741052 cites W2798239553 @default.
• W2739741052 cites W2952825952 @default.
• W2739741052 cites W2964100269 @default.
• W2739741052 cites W2964309400 @default.
• W2739741052 cites W3020853991 @default.
• W2739741052 cites W3099491577 @default.
• W2739741052 cites W3102317997 @default.
• W2739741052 cites W3106144113 @default.
• W2739741052 hasPublicationYear "2017" @default.
• W2739741052 type Work @default.
• W2739741052 sameAs 2739741052 @default.
• W2739741052 citedByCount "11" @default.
• W2739741052 countsByYear W27397410522019 @default.
• W2739741052 countsByYear W27397410522020 @default.
• W2739741052 countsByYear W27397410522021 @default.
• W2739741052 crossrefType "proceedings-article" @default.
• W2739741052 hasAuthorship W2739741052A5061293973 @default.
• W2739741052 hasAuthorship W2739741052A5068048142 @default.
• W2739741052 hasConcept C101468663 @default.
• W2739741052 hasConcept C108583219 @default.
• W2739741052 hasConcept C109546454 @default.
• W2739741052 hasConcept C111919701 @default.
• W2739741052 hasConcept C119857082 @default.
• W2739741052 hasConcept C121332964 @default.
• W2739741052 hasConcept C12520029 @default.
• W2739741052 hasConcept C127413603 @default.
• W2739741052 hasConcept C154945302 @default.
• W2739741052 hasConcept C166957645 @default.
• W2739741052 hasConcept C168167062 @default.
• W2739741052 hasConcept C175202392 @default.
• W2739741052 hasConcept C176217482 @default.
• W2739741052 hasConcept C190470478 @default.
• W2739741052 hasConcept C195065555 @default.
• W2739741052 hasConcept C21547014 @default.
• W2739741052 hasConcept C2524010 @default.
• W2739741052 hasConcept C2776608160 @default.
• W2739741052 hasConcept C2781121602 @default.
• W2739741052 hasConcept C29406490 @default.
• W2739741052 hasConcept C2984842247 @default.
• W2739741052 hasConcept C33923547 @default.
• W2739741052 hasConcept C37914503 @default.
• W2739741052 hasConcept C41008148 @default.
• W2739741052 hasConcept C50644808 @default.
• W2739741052 hasConcept C80444323 @default.
• W2739741052 hasConcept C95457728 @default.
• W2739741052 hasConcept C97355855 @default.
• W2739741052 hasConceptScore W2739741052C101468663 @default.
• W2739741052 hasConceptScore W2739741052C108583219 @default.
• W2739741052 hasConceptScore W2739741052C109546454 @default.
• W2739741052 hasConceptScore W2739741052C111919701 @default.
• W2739741052 hasConceptScore W2739741052C119857082 @default.
• W2739741052 hasConceptScore W2739741052C121332964 @default.
• W2739741052 hasConceptScore W2739741052C12520029 @default.
• W2739741052 hasConceptScore W2739741052C127413603 @default.

• next