Matches in SemOpenAlex for { <https://semopenalex.org/work/W1488860675> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W1488860675 abstract "Networks of goal seeking neurons (GSN) are weightless models that were designed to overcome several problems with PLN networks. Weightless (Boolean) models are well-known by their ease to implement on hardware and software. Some hardware implementations and general improvements have been proposed for these models specially to perform better with their main target task: classification. In this work, the union of two earlier improvements is proposed and tested on classifiers that use GSN networks as their building blocks on a handwritten digit recognition task. Both improvements aim to maximize the number of learned examples. The GSN expansion strategy decreases saturation problems while the adaptation of presentation order modifies the sequence of patterns based on the GSN network behavior itself: GSN uses a fast one-shot learning algorithm when it is not allowed to modify used positions. Therefore, during the training, several examples are refused by the net since it cannot be learned. This behavior indicates when a GSN network is saturated. By using the idea of expanding the network when it is needed, it is possible to overcome this limitation. The adaptive order procedure improves the network learning since it allows difficult examples to be presented before easier ones. Results of simulations show the combined improvement leads to significant gains of performance. Moreover, some ideas can be applied on many other neural models." @default.
- W1488860675 created "2016-06-24" @default.
- W1488860675 creator A5066995388 @default.
- W1488860675 creator A5068929842 @default.
- W1488860675 date "2002-11-13" @default.
- W1488860675 modified "2023-09-26" @default.
- W1488860675 title "Improving GSN classifiers using expansion and adaptive presentation order" @default.
- W1488860675 cites W1512838124 @default.
- W1488860675 cites W190992373 @default.
- W1488860675 cites W1995341919 @default.
- W1488860675 cites W1995426156 @default.
- W1488860675 cites W2037529930 @default.
- W1488860675 cites W2041998425 @default.
- W1488860675 cites W2130514843 @default.
- W1488860675 doi "https://doi.org/10.1109/ijcnn.2001.938477" @default.
- W1488860675 hasPublicationYear "2002" @default.
- W1488860675 type Work @default.
- W1488860675 sameAs 1488860675 @default.
- W1488860675 citedByCount "0" @default.
- W1488860675 crossrefType "proceedings-article" @default.
- W1488860675 hasAuthorship W1488860675A5066995388 @default.
- W1488860675 hasAuthorship W1488860675A5068929842 @default.
- W1488860675 hasConcept C113775141 @default.
- W1488860675 hasConcept C115903868 @default.
- W1488860675 hasConcept C119857082 @default.
- W1488860675 hasConcept C120665830 @default.
- W1488860675 hasConcept C121332964 @default.
- W1488860675 hasConcept C126838900 @default.
- W1488860675 hasConcept C139807058 @default.
- W1488860675 hasConcept C154945302 @default.
- W1488860675 hasConcept C162324750 @default.
- W1488860675 hasConcept C187736073 @default.
- W1488860675 hasConcept C199360897 @default.
- W1488860675 hasConcept C26713055 @default.
- W1488860675 hasConcept C2777601897 @default.
- W1488860675 hasConcept C2777904410 @default.
- W1488860675 hasConcept C2780451532 @default.
- W1488860675 hasConcept C41008148 @default.
- W1488860675 hasConcept C50644808 @default.
- W1488860675 hasConcept C71924100 @default.
- W1488860675 hasConceptScore W1488860675C113775141 @default.
- W1488860675 hasConceptScore W1488860675C115903868 @default.
- W1488860675 hasConceptScore W1488860675C119857082 @default.
- W1488860675 hasConceptScore W1488860675C120665830 @default.
- W1488860675 hasConceptScore W1488860675C121332964 @default.
- W1488860675 hasConceptScore W1488860675C126838900 @default.
- W1488860675 hasConceptScore W1488860675C139807058 @default.
- W1488860675 hasConceptScore W1488860675C154945302 @default.
- W1488860675 hasConceptScore W1488860675C162324750 @default.
- W1488860675 hasConceptScore W1488860675C187736073 @default.
- W1488860675 hasConceptScore W1488860675C199360897 @default.
- W1488860675 hasConceptScore W1488860675C26713055 @default.
- W1488860675 hasConceptScore W1488860675C2777601897 @default.
- W1488860675 hasConceptScore W1488860675C2777904410 @default.
- W1488860675 hasConceptScore W1488860675C2780451532 @default.
- W1488860675 hasConceptScore W1488860675C41008148 @default.
- W1488860675 hasConceptScore W1488860675C50644808 @default.
- W1488860675 hasConceptScore W1488860675C71924100 @default.
- W1488860675 hasLocation W14888606751 @default.
- W1488860675 hasOpenAccess W1488860675 @default.
- W1488860675 hasPrimaryLocation W14888606751 @default.
- W1488860675 hasRelatedWork W1867797766 @default.
- W1488860675 hasRelatedWork W2049139666 @default.
- W1488860675 hasRelatedWork W2141653139 @default.
- W1488860675 hasRelatedWork W2267788219 @default.
- W1488860675 hasRelatedWork W2310900080 @default.
- W1488860675 hasRelatedWork W2350265014 @default.
- W1488860675 hasRelatedWork W2362290929 @default.
- W1488860675 hasRelatedWork W2948422470 @default.
- W1488860675 hasRelatedWork W3097428511 @default.
- W1488860675 hasRelatedWork W3107474891 @default.
- W1488860675 isParatext "false" @default.
- W1488860675 isRetracted "false" @default.
- W1488860675 magId "1488860675" @default.
- W1488860675 workType "article" @default.