Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201615216> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W3201615216 endingPage "536" @default.
- W3201615216 startingPage "525" @default.
- W3201615216 abstract "The ability to develop representations of components and to recombine them in a new but compositionally meaningful manner is considered a hallmark of human cognition, which has not been reached by machines, yet. The Omniglot challenge taps into this deficit by posing several one-shot/few-shot generation and classification tasks of handwritten character trajectories. In contrast to the original approach of providing character components, we investigated how compositional representations can develop naturally within a generative LSTM model. The network’s performance and the underlying mechanisms are examined on the original Omniglot dataset and on our own more representative dataset. We show that solving the challenge becomes possible, because, during training, the designed LSTM network fosters the learning of compositional representations, which it can quickly reassemble into new, unseen but related character trajectories. Evidence is provided by several experiments, including an analysis of the latent states of the system, revealing the emergent compositional structures with t-SNE, and the evaluation of the network’s performance, when training and test alphabets do or do not share components. Overall, we show how compositionality can be fostered in latent, generative encodings, thus improving machine learning by further aligning technical methods to cognitive mechanisms in humans." @default.
- W3201615216 created "2021-09-27" @default.
- W3201615216 creator A5030096952 @default.
- W3201615216 creator A5036718594 @default.
- W3201615216 creator A5075919503 @default.
- W3201615216 date "2021-01-01" @default.
- W3201615216 modified "2023-09-23" @default.
- W3201615216 title "Fostering Compositionality in Latent, Generative Encodings to Solve the Omniglot Challenge" @default.
- W3201615216 cites W2064675550 @default.
- W3201615216 cites W2194321275 @default.
- W3201615216 cites W2197913588 @default.
- W3201615216 cites W2765332150 @default.
- W3201615216 cites W2961719374 @default.
- W3201615216 cites W2963305465 @default.
- W3201615216 cites W2963387406 @default.
- W3201615216 cites W3008058947 @default.
- W3201615216 cites W3013208650 @default.
- W3201615216 cites W3017374003 @default.
- W3201615216 cites W3095242799 @default.
- W3201615216 doi "https://doi.org/10.1007/978-3-030-86340-1_42" @default.
- W3201615216 hasPublicationYear "2021" @default.
- W3201615216 type Work @default.
- W3201615216 sameAs 3201615216 @default.
- W3201615216 citedByCount "2" @default.
- W3201615216 countsByYear W32016152162023 @default.
- W3201615216 crossrefType "book-chapter" @default.
- W3201615216 hasAuthorship W3201615216A5030096952 @default.
- W3201615216 hasAuthorship W3201615216A5036718594 @default.
- W3201615216 hasAuthorship W3201615216A5075919503 @default.
- W3201615216 hasConcept C119857082 @default.
- W3201615216 hasConcept C121375916 @default.
- W3201615216 hasConcept C154945302 @default.
- W3201615216 hasConcept C167966045 @default.
- W3201615216 hasConcept C204321447 @default.
- W3201615216 hasConcept C2524010 @default.
- W3201615216 hasConcept C2776502983 @default.
- W3201615216 hasConcept C2780861071 @default.
- W3201615216 hasConcept C33923547 @default.
- W3201615216 hasConcept C39890363 @default.
- W3201615216 hasConcept C41008148 @default.
- W3201615216 hasConceptScore W3201615216C119857082 @default.
- W3201615216 hasConceptScore W3201615216C121375916 @default.
- W3201615216 hasConceptScore W3201615216C154945302 @default.
- W3201615216 hasConceptScore W3201615216C167966045 @default.
- W3201615216 hasConceptScore W3201615216C204321447 @default.
- W3201615216 hasConceptScore W3201615216C2524010 @default.
- W3201615216 hasConceptScore W3201615216C2776502983 @default.
- W3201615216 hasConceptScore W3201615216C2780861071 @default.
- W3201615216 hasConceptScore W3201615216C33923547 @default.
- W3201615216 hasConceptScore W3201615216C39890363 @default.
- W3201615216 hasConceptScore W3201615216C41008148 @default.
- W3201615216 hasLocation W32016152161 @default.
- W3201615216 hasOpenAccess W3201615216 @default.
- W3201615216 hasPrimaryLocation W32016152161 @default.
- W3201615216 hasRelatedWork W1534961803 @default.
- W3201615216 hasRelatedWork W2108501770 @default.
- W3201615216 hasRelatedWork W2884815824 @default.
- W3201615216 hasRelatedWork W2896809929 @default.
- W3201615216 hasRelatedWork W2994891734 @default.
- W3201615216 hasRelatedWork W4241824423 @default.
- W3201615216 hasRelatedWork W4293428270 @default.
- W3201615216 hasRelatedWork W4310743516 @default.
- W3201615216 hasRelatedWork W4323363096 @default.
- W3201615216 hasRelatedWork W2310403681 @default.
- W3201615216 isParatext "false" @default.
- W3201615216 isRetracted "false" @default.
- W3201615216 magId "3201615216" @default.
- W3201615216 workType "book-chapter" @default.