Matches in SemOpenAlex for { <https://semopenalex.org/work/W2061710666> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2061710666 endingPage "204" @default.
- W2061710666 startingPage "195" @default.
- W2061710666 abstract "The issue of training a neural network to approximate a multivariate function is addressed at length in the current literature. The lack of a non-iterative or closed form solution for the weights of sigmoid neural networks motivates an alternate view of neural networks. It has long been known that Cerebellar Model Articulation Controller-type networks are able to approximate multivariate functions, as well as being directly programmable given a training data set. CMAC networks, however, suffer from the curse of dimensionality regarding the exponential growth in the number of receptive field functions that must be employed as the dimension of the function increases. The work in this paper studies the use of networks that limit the number of dimensions onto which high dimensional functions must be projected for approximation purposes. While preserving the direct programmability of CMAC networks, the work here uses frequency information about the function to limit the number of couplings used in the approximation. It is shown that for bandlimited functions, the number of network parameters or weights required to achieve zero approximation error has only a polynomial growth with dimension. At the conclusion of the paper, a procedure is given for estimating the size of a CMAC network based on the frequency bandwidth of the function to be approximated." @default.
- W2061710666 created "2016-06-24" @default.
- W2061710666 creator A5039658470 @default.
- W2061710666 creator A5042833838 @default.
- W2061710666 date "2002-01-01" @default.
- W2061710666 modified "2023-09-25" @default.
- W2061710666 title "The Limited Coupling Approximation with Application to CMAC Networks" @default.
- W2061710666 cites W1991932501 @default.
- W2061710666 cites W1998087100 @default.
- W2061710666 cites W2005971284 @default.
- W2061710666 cites W2019006876 @default.
- W2061710666 cites W2069683962 @default.
- W2061710666 cites W2096443901 @default.
- W2061710666 cites W2096835548 @default.
- W2061710666 cites W2104030629 @default.
- W2061710666 cites W2109189741 @default.
- W2061710666 cites W2127919919 @default.
- W2061710666 cites W2130945372 @default.
- W2061710666 cites W2136417576 @default.
- W2061710666 cites W2140256789 @default.
- W2061710666 cites W2142763620 @default.
- W2061710666 cites W2150535417 @default.
- W2061710666 cites W2151621437 @default.
- W2061710666 cites W2152619728 @default.
- W2061710666 cites W2155399784 @default.
- W2061710666 cites W2167501416 @default.
- W2061710666 cites W2168985088 @default.
- W2061710666 cites W4235652767 @default.
- W2061710666 cites W4238957295 @default.
- W2061710666 cites W4249925659 @default.
- W2061710666 cites W4302104822 @default.
- W2061710666 doi "https://doi.org/10.1080/10255810213477" @default.
- W2061710666 hasPublicationYear "2002" @default.
- W2061710666 type Work @default.
- W2061710666 sameAs 2061710666 @default.
- W2061710666 citedByCount "0" @default.
- W2061710666 crossrefType "journal-article" @default.
- W2061710666 hasAuthorship W2061710666A5039658470 @default.
- W2061710666 hasAuthorship W2061710666A5042833838 @default.
- W2061710666 hasConcept C102519508 @default.
- W2061710666 hasConcept C111030470 @default.
- W2061710666 hasConcept C11413529 @default.
- W2061710666 hasConcept C126255220 @default.
- W2061710666 hasConcept C129997835 @default.
- W2061710666 hasConcept C134306372 @default.
- W2061710666 hasConcept C151201525 @default.
- W2061710666 hasConcept C154945302 @default.
- W2061710666 hasConcept C202444582 @default.
- W2061710666 hasConcept C2780576740 @default.
- W2061710666 hasConcept C28826006 @default.
- W2061710666 hasConcept C33676613 @default.
- W2061710666 hasConcept C33923547 @default.
- W2061710666 hasConcept C41008148 @default.
- W2061710666 hasConcept C50644808 @default.
- W2061710666 hasConcept C81388566 @default.
- W2061710666 hasConcept C91873725 @default.
- W2061710666 hasConceptScore W2061710666C102519508 @default.
- W2061710666 hasConceptScore W2061710666C111030470 @default.
- W2061710666 hasConceptScore W2061710666C11413529 @default.
- W2061710666 hasConceptScore W2061710666C126255220 @default.
- W2061710666 hasConceptScore W2061710666C129997835 @default.
- W2061710666 hasConceptScore W2061710666C134306372 @default.
- W2061710666 hasConceptScore W2061710666C151201525 @default.
- W2061710666 hasConceptScore W2061710666C154945302 @default.
- W2061710666 hasConceptScore W2061710666C202444582 @default.
- W2061710666 hasConceptScore W2061710666C2780576740 @default.
- W2061710666 hasConceptScore W2061710666C28826006 @default.
- W2061710666 hasConceptScore W2061710666C33676613 @default.
- W2061710666 hasConceptScore W2061710666C33923547 @default.
- W2061710666 hasConceptScore W2061710666C41008148 @default.
- W2061710666 hasConceptScore W2061710666C50644808 @default.
- W2061710666 hasConceptScore W2061710666C81388566 @default.
- W2061710666 hasConceptScore W2061710666C91873725 @default.
- W2061710666 hasIssue "3" @default.
- W2061710666 hasLocation W20617106661 @default.
- W2061710666 hasOpenAccess W2061710666 @default.
- W2061710666 hasPrimaryLocation W20617106661 @default.
- W2061710666 hasRelatedWork W1968866874 @default.
- W2061710666 hasRelatedWork W2061710666 @default.
- W2061710666 hasRelatedWork W2097165092 @default.
- W2061710666 hasRelatedWork W2114873881 @default.
- W2061710666 hasRelatedWork W2370639576 @default.
- W2061710666 hasRelatedWork W3144708166 @default.
- W2061710666 hasRelatedWork W3192236647 @default.
- W2061710666 hasRelatedWork W3216202101 @default.
- W2061710666 hasRelatedWork W4281553196 @default.
- W2061710666 hasRelatedWork W4287241094 @default.
- W2061710666 hasVolume "4" @default.
- W2061710666 isParatext "false" @default.
- W2061710666 isRetracted "false" @default.
- W2061710666 magId "2061710666" @default.
- W2061710666 workType "article" @default.