Matches in SemOpenAlex for { <https://semopenalex.org/work/W2048818575> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2048818575 abstract "A simple dynamic model of a neural network is presented. Using the dynamic model of a neural network, we improve the performance of a three-layer multilayer perceptron (MLP). The dynamic model of a MLP is used to make fundamental changes in the network optimization strategy. These changes are: Neuron activation functions are used, which reduce the probability of singular Jacobians; Successive regularization is used to constrain the volume of the weight space being minimized; Boltzmann pruning is used to constrain the dimension of the weight space; and prior class probabilities are used to normalize all error calculations, so that statistically significant samples of rare but important classes can be included without distortion of the error surface. All four of these changes are made in the inner loop of a conjugate gradient optimization iteration and are intended to simplify the training dynamics ofthe optimization. On handprinted digits and fingerprint classification problems, these modifications improve error-reject performance by factors between 2 and 4 and reduce network size by 40 to 60%." @default.
- W2048818575 created "2016-06-24" @default.
- W2048818575 creator A5019296318 @default.
- W2048818575 creator A5026331459 @default.
- W2048818575 creator A5059585674 @default.
- W2048818575 date "1997-07-01" @default.
- W2048818575 modified "2023-09-24" @default.
- W2048818575 title "Neurodynamics of learning and network performance" @default.
- W2048818575 cites W1495264186 @default.
- W2048818575 cites W1561704653 @default.
- W2048818575 cites W1603340857 @default.
- W2048818575 cites W1770825568 @default.
- W2048818575 cites W1970150866 @default.
- W2048818575 cites W1973189438 @default.
- W2048818575 cites W1977106683 @default.
- W2048818575 cites W1977923618 @default.
- W2048818575 cites W1990274295 @default.
- W2048818575 cites W1991848143 @default.
- W2048818575 cites W2000711743 @default.
- W2048818575 cites W2033432003 @default.
- W2048818575 cites W2042492924 @default.
- W2048818575 cites W2047029283 @default.
- W2048818575 cites W2062210787 @default.
- W2048818575 cites W2072773743 @default.
- W2048818575 cites W2078206416 @default.
- W2048818575 cites W2089876099 @default.
- W2048818575 cites W2094169479 @default.
- W2048818575 cites W2135346934 @default.
- W2048818575 cites W2626807718 @default.
- W2048818575 cites W3172363867 @default.
- W2048818575 doi "https://doi.org/10.1117/12.272656" @default.
- W2048818575 hasPublicationYear "1997" @default.
- W2048818575 type Work @default.
- W2048818575 sameAs 2048818575 @default.
- W2048818575 citedByCount "4" @default.
- W2048818575 crossrefType "journal-article" @default.
- W2048818575 hasAuthorship W2048818575A5019296318 @default.
- W2048818575 hasAuthorship W2048818575A5026331459 @default.
- W2048818575 hasAuthorship W2048818575A5059585674 @default.
- W2048818575 hasConcept C11413529 @default.
- W2048818575 hasConcept C153180895 @default.
- W2048818575 hasConcept C153258448 @default.
- W2048818575 hasConcept C154945302 @default.
- W2048818575 hasConcept C155032097 @default.
- W2048818575 hasConcept C192576344 @default.
- W2048818575 hasConcept C2776135515 @default.
- W2048818575 hasConcept C41008148 @default.
- W2048818575 hasConcept C50644808 @default.
- W2048818575 hasConcept C60908668 @default.
- W2048818575 hasConcept C81184566 @default.
- W2048818575 hasConceptScore W2048818575C11413529 @default.
- W2048818575 hasConceptScore W2048818575C153180895 @default.
- W2048818575 hasConceptScore W2048818575C153258448 @default.
- W2048818575 hasConceptScore W2048818575C154945302 @default.
- W2048818575 hasConceptScore W2048818575C155032097 @default.
- W2048818575 hasConceptScore W2048818575C192576344 @default.
- W2048818575 hasConceptScore W2048818575C2776135515 @default.
- W2048818575 hasConceptScore W2048818575C41008148 @default.
- W2048818575 hasConceptScore W2048818575C50644808 @default.
- W2048818575 hasConceptScore W2048818575C60908668 @default.
- W2048818575 hasConceptScore W2048818575C81184566 @default.
- W2048818575 hasLocation W20488185751 @default.
- W2048818575 hasOpenAccess W2048818575 @default.
- W2048818575 hasPrimaryLocation W20488185751 @default.
- W2048818575 hasRelatedWork W1502970866 @default.
- W2048818575 hasRelatedWork W1980798878 @default.
- W2048818575 hasRelatedWork W1990981226 @default.
- W2048818575 hasRelatedWork W2044527973 @default.
- W2048818575 hasRelatedWork W2054378925 @default.
- W2048818575 hasRelatedWork W2109788599 @default.
- W2048818575 hasRelatedWork W2126644291 @default.
- W2048818575 hasRelatedWork W2135520967 @default.
- W2048818575 hasRelatedWork W2150732662 @default.
- W2048818575 hasRelatedWork W2150781240 @default.
- W2048818575 hasRelatedWork W2160821628 @default.
- W2048818575 hasRelatedWork W2161297370 @default.
- W2048818575 hasRelatedWork W2169230781 @default.
- W2048818575 hasRelatedWork W2185948460 @default.
- W2048818575 hasRelatedWork W2320002117 @default.
- W2048818575 hasRelatedWork W2353091813 @default.
- W2048818575 hasRelatedWork W2547938545 @default.
- W2048818575 hasRelatedWork W2563146207 @default.
- W2048818575 hasRelatedWork W2965628765 @default.
- W2048818575 hasRelatedWork W3122455256 @default.
- W2048818575 isParatext "false" @default.
- W2048818575 isRetracted "false" @default.
- W2048818575 magId "2048818575" @default.
- W2048818575 workType "article" @default.