Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385373755> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4385373755 abstract "It is often useful to perform integration over learned functions represented by neural networks. However, this integration is usually performed numerically, as analytical integration over learned functions (especially neural networks) is generally viewed as intractable. In this work, we present a method for representing the analytical integral of a learned function $f$. This allows the exact integral of a neural network to be computed, and enables constrained neural networks to be parametrised by applying constraints directly to the integral. Crucially, we also introduce a method to constrain $f$ to be positive, a necessary condition for many applications (e.g. probability distributions, distance metrics, etc). Finally, we introduce several applications where our fixed-integral neural network (FINN) can be utilised." @default.
- W4385373755 created "2023-07-29" @default.
- W4385373755 creator A5068296171 @default.
- W4385373755 date "2023-07-26" @default.
- W4385373755 modified "2023-10-12" @default.
- W4385373755 title "Fixed Integral Neural Networks" @default.
- W4385373755 doi "https://doi.org/10.48550/arxiv.2307.14439" @default.
- W4385373755 hasPublicationYear "2023" @default.
- W4385373755 type Work @default.
- W4385373755 citedByCount "0" @default.
- W4385373755 crossrefType "posted-content" @default.
- W4385373755 hasAuthorship W4385373755A5068296171 @default.
- W4385373755 hasBestOaLocation W43853737551 @default.
- W4385373755 hasConcept C101812284 @default.
- W4385373755 hasConcept C127349201 @default.
- W4385373755 hasConcept C134306372 @default.
- W4385373755 hasConcept C14036430 @default.
- W4385373755 hasConcept C154945302 @default.
- W4385373755 hasConcept C27016315 @default.
- W4385373755 hasConcept C28826006 @default.
- W4385373755 hasConcept C33923547 @default.
- W4385373755 hasConcept C41008148 @default.
- W4385373755 hasConcept C50644808 @default.
- W4385373755 hasConcept C54865166 @default.
- W4385373755 hasConcept C78458016 @default.
- W4385373755 hasConcept C86803240 @default.
- W4385373755 hasConceptScore W4385373755C101812284 @default.
- W4385373755 hasConceptScore W4385373755C127349201 @default.
- W4385373755 hasConceptScore W4385373755C134306372 @default.
- W4385373755 hasConceptScore W4385373755C14036430 @default.
- W4385373755 hasConceptScore W4385373755C154945302 @default.
- W4385373755 hasConceptScore W4385373755C27016315 @default.
- W4385373755 hasConceptScore W4385373755C28826006 @default.
- W4385373755 hasConceptScore W4385373755C33923547 @default.
- W4385373755 hasConceptScore W4385373755C41008148 @default.
- W4385373755 hasConceptScore W4385373755C50644808 @default.
- W4385373755 hasConceptScore W4385373755C54865166 @default.
- W4385373755 hasConceptScore W4385373755C78458016 @default.
- W4385373755 hasConceptScore W4385373755C86803240 @default.
- W4385373755 hasLocation W43853737551 @default.
- W4385373755 hasOpenAccess W4385373755 @default.
- W4385373755 hasPrimaryLocation W43853737551 @default.
- W4385373755 hasRelatedWork W1972957018 @default.
- W4385373755 hasRelatedWork W2029225192 @default.
- W4385373755 hasRelatedWork W2043842112 @default.
- W4385373755 hasRelatedWork W2081496544 @default.
- W4385373755 hasRelatedWork W2106724865 @default.
- W4385373755 hasRelatedWork W2382091622 @default.
- W4385373755 hasRelatedWork W2389169342 @default.
- W4385373755 hasRelatedWork W2392362156 @default.
- W4385373755 hasRelatedWork W4230841224 @default.
- W4385373755 hasRelatedWork W4233593527 @default.
- W4385373755 isParatext "false" @default.
- W4385373755 isRetracted "false" @default.
- W4385373755 workType "article" @default.