Matches in SemOpenAlex for { <https://semopenalex.org/work/W2977653913> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2977653913 abstract "The study of universal approximation of arbitrary functions $f: mathcal{X} to mathcal{Y}$ by neural networks has a rich and thorough history dating back to Kolmogorov (1957). In the case of learning finite dimensional maps, many authors have shown various forms of the universality of both fixed depth and fixed width neural networks. However, in many cases, these classical results fail to extend to the recent use of approximations of neural networks with infinitely many units for functional data analysis, dynamical systems identification, and other applications where either $mathcal{X}$ or $mathcal{Y}$ become infinite dimensional. Two questions naturally arise: which infinite dimensional analogues of neural networks are sufficient to approximate any map $f: mathcal{X} to mathcal{Y}$, and when do the finite approximations to these analogues used in practice approximate $f$ uniformly over its infinite dimensional domain $mathcal{X}$? In this paper, we answer the open question of universal approximation of nonlinear operators when $mathcal{X}$ and $mathcal{Y}$ are both infinite dimensional. We show that for a large class of different infinite analogues of neural networks, any continuous map can be approximated arbitrarily closely with some mild topological conditions on $mathcal{X}$. Additionally, we provide the first lower-bound on the minimal number of input and output units required by a finite approximation to an infinite neural network to guarantee that it can uniformly approximate any nonlinear operator using samples from its inputs and outputs." @default.
- W2977653913 created "2019-10-10" @default.
- W2977653913 creator A5065253486 @default.
- W2977653913 creator A5071983998 @default.
- W2977653913 date "2019-10-03" @default.
- W2977653913 modified "2023-09-27" @default.
- W2977653913 title "On Universal Approximation by Neural Networks with Uniform Guarantees on Approximation of Infinite Dimensional Maps" @default.
- W2977653913 cites W1988115241 @default.
- W2977653913 cites W1994005439 @default.
- W2977653913 cites W2036614784 @default.
- W2977653913 cites W2046023874 @default.
- W2977653913 cites W2103496339 @default.
- W2977653913 cites W2139923370 @default.
- W2977653913 cites W2212676342 @default.
- W2977653913 cites W2741317041 @default.
- W2977653913 cites W2752387826 @default.
- W2977653913 cites W3021971632 @default.
- W2977653913 cites W3101765447 @default.
- W2977653913 cites W2136846412 @default.
- W2977653913 hasPublicationYear "2019" @default.
- W2977653913 type Work @default.
- W2977653913 sameAs 2977653913 @default.
- W2977653913 citedByCount "5" @default.
- W2977653913 countsByYear W29776539132020 @default.
- W2977653913 countsByYear W29776539132021 @default.
- W2977653913 crossrefType "posted-content" @default.
- W2977653913 hasAuthorship W2977653913A5065253486 @default.
- W2977653913 hasAuthorship W2977653913A5071983998 @default.
- W2977653913 hasConcept C114614502 @default.
- W2977653913 hasConcept C118615104 @default.
- W2977653913 hasConcept C121332964 @default.
- W2977653913 hasConcept C154945302 @default.
- W2977653913 hasConcept C158622935 @default.
- W2977653913 hasConcept C183992945 @default.
- W2977653913 hasConcept C184720557 @default.
- W2977653913 hasConcept C193386753 @default.
- W2977653913 hasConcept C202444582 @default.
- W2977653913 hasConcept C28826006 @default.
- W2977653913 hasConcept C33923547 @default.
- W2977653913 hasConcept C41008148 @default.
- W2977653913 hasConcept C50644808 @default.
- W2977653913 hasConcept C62520636 @default.
- W2977653913 hasConceptScore W2977653913C114614502 @default.
- W2977653913 hasConceptScore W2977653913C118615104 @default.
- W2977653913 hasConceptScore W2977653913C121332964 @default.
- W2977653913 hasConceptScore W2977653913C154945302 @default.
- W2977653913 hasConceptScore W2977653913C158622935 @default.
- W2977653913 hasConceptScore W2977653913C183992945 @default.
- W2977653913 hasConceptScore W2977653913C184720557 @default.
- W2977653913 hasConceptScore W2977653913C193386753 @default.
- W2977653913 hasConceptScore W2977653913C202444582 @default.
- W2977653913 hasConceptScore W2977653913C28826006 @default.
- W2977653913 hasConceptScore W2977653913C33923547 @default.
- W2977653913 hasConceptScore W2977653913C41008148 @default.
- W2977653913 hasConceptScore W2977653913C50644808 @default.
- W2977653913 hasConceptScore W2977653913C62520636 @default.
- W2977653913 hasLocation W29776539131 @default.
- W2977653913 hasOpenAccess W2977653913 @default.
- W2977653913 hasPrimaryLocation W29776539131 @default.
- W2977653913 hasRelatedWork W1410304813 @default.
- W2977653913 hasRelatedWork W1510704178 @default.
- W2977653913 hasRelatedWork W1514590462 @default.
- W2977653913 hasRelatedWork W2027976307 @default.
- W2977653913 hasRelatedWork W2038814103 @default.
- W2977653913 hasRelatedWork W2067321622 @default.
- W2977653913 hasRelatedWork W2096534942 @default.
- W2977653913 hasRelatedWork W2230446138 @default.
- W2977653913 hasRelatedWork W2261074125 @default.
- W2977653913 hasRelatedWork W2490078038 @default.
- W2977653913 hasRelatedWork W2530120746 @default.
- W2977653913 hasRelatedWork W2768900956 @default.
- W2977653913 hasRelatedWork W2950779159 @default.
- W2977653913 hasRelatedWork W2962959080 @default.
- W2977653913 hasRelatedWork W2963417526 @default.
- W2977653913 hasRelatedWork W3105440173 @default.
- W2977653913 hasRelatedWork W3133520142 @default.
- W2977653913 hasRelatedWork W3196141392 @default.
- W2977653913 hasRelatedWork W342935888 @default.
- W2977653913 hasRelatedWork W3151649156 @default.
- W2977653913 isParatext "false" @default.
- W2977653913 isRetracted "false" @default.
- W2977653913 magId "2977653913" @default.
- W2977653913 workType "article" @default.