Matches in SemOpenAlex for { <https://semopenalex.org/work/W1616695905> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W1616695905 abstract "The neocognitron is a multi-layered convolutional network that can be trained to recognize visual patterns robustly. In the intermediate layers of the neocognitron, local features are extracted from input patterns. In the highest (or deepest) layers of the network, the method of Interpolating-Vector is used for classifying patterns based on the features extracted by the intermediate layers. During the learning, several reference vectors for each class are created from a set of training vectors. To recognize an input vector, we measure distances (based on similarities) between the input vector and planes that are spanned by every trio of reference vectors of the same class. The class name of the nearest plane is taken as the result of classification. To reduce the computational cost, we propose to search the nearest plane, not among all possible combinations of three reference vectors, but only among trios that contain the nearest reference vector. For reducing the computational cost, it is also important to represent the large number of training vectors accurately with a compact set of reference vectors. To create a compact set of reference vectors, the learning is carried out in two steps. In the first step, reference vectors are just chosen from vectors in the training set. We start modifying reference vectors (namely, fine tuning of connections) from the second step after an enough number of reference vectors have been chosen. The effectiveness of the proposed method for recognizing hand-written digits is demonstrated by computer simulation." @default.
- W1616695905 created "2016-06-24" @default.
- W1616695905 creator A5064042196 @default.
- W1616695905 creator A5087391146 @default.
- W1616695905 date "2015-07-01" @default.
- W1616695905 modified "2023-09-26" @default.
- W1616695905 title "Deep convolutional network neocognitron: Improved Interpolating-Vector" @default.
- W1616695905 cites W1981914622 @default.
- W1616695905 cites W2055854250 @default.
- W1616695905 cites W2063063428 @default.
- W1616695905 cites W2076063813 @default.
- W1616695905 cites W2100281586 @default.
- W1616695905 cites W2101926813 @default.
- W1616695905 cites W2130325614 @default.
- W1616695905 cites W2134184411 @default.
- W1616695905 cites W2136922672 @default.
- W1616695905 cites W2146076056 @default.
- W1616695905 cites W2153635508 @default.
- W1616695905 cites W351354842 @default.
- W1616695905 cites W4231109964 @default.
- W1616695905 doi "https://doi.org/10.1109/ijcnn.2015.7280514" @default.
- W1616695905 hasPublicationYear "2015" @default.
- W1616695905 type Work @default.
- W1616695905 sameAs 1616695905 @default.
- W1616695905 citedByCount "6" @default.
- W1616695905 countsByYear W16166959052016 @default.
- W1616695905 countsByYear W16166959052018 @default.
- W1616695905 countsByYear W16166959052019 @default.
- W1616695905 countsByYear W16166959052021 @default.
- W1616695905 countsByYear W16166959052022 @default.
- W1616695905 crossrefType "proceedings-article" @default.
- W1616695905 hasAuthorship W1616695905A5064042196 @default.
- W1616695905 hasAuthorship W1616695905A5087391146 @default.
- W1616695905 hasConcept C121144440 @default.
- W1616695905 hasConcept C154945302 @default.
- W1616695905 hasConcept C175202392 @default.
- W1616695905 hasConcept C28490314 @default.
- W1616695905 hasConcept C41008148 @default.
- W1616695905 hasConcept C50644808 @default.
- W1616695905 hasConcept C81363708 @default.
- W1616695905 hasConceptScore W1616695905C121144440 @default.
- W1616695905 hasConceptScore W1616695905C154945302 @default.
- W1616695905 hasConceptScore W1616695905C175202392 @default.
- W1616695905 hasConceptScore W1616695905C28490314 @default.
- W1616695905 hasConceptScore W1616695905C41008148 @default.
- W1616695905 hasConceptScore W1616695905C50644808 @default.
- W1616695905 hasConceptScore W1616695905C81363708 @default.
- W1616695905 hasLocation W16166959051 @default.
- W1616695905 hasOpenAccess W1616695905 @default.
- W1616695905 hasPrimaryLocation W16166959051 @default.
- W1616695905 hasRelatedWork W2285788670 @default.
- W1616695905 hasRelatedWork W2735477435 @default.
- W1616695905 hasRelatedWork W2760207603 @default.
- W1616695905 hasRelatedWork W2763109982 @default.
- W1616695905 hasRelatedWork W2955938200 @default.
- W1616695905 hasRelatedWork W2976316911 @default.
- W1616695905 hasRelatedWork W2998526951 @default.
- W1616695905 hasRelatedWork W3046083774 @default.
- W1616695905 hasRelatedWork W3091408200 @default.
- W1616695905 hasRelatedWork W3156786002 @default.
- W1616695905 isParatext "false" @default.
- W1616695905 isRetracted "false" @default.
- W1616695905 magId "1616695905" @default.
- W1616695905 workType "article" @default.