Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385484759> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4385484759 abstract "Spiking Neural Networks (SNNs) remain on the fringe of machine learning research despite their potential for fast low-power performance and fully local operation, including rapid online learning, on edge computing devices. In SNNs, encoding information in the timing of individual spikes is more efficient than using spiking rates for which many spikes are required. However, combining spike-time coding with unsupervised learning has proven somewhat challenging. Here we use spike latency coding with local unsupervised spike-timing-dependent plasticity and several biologically inspired local homeostatic mechanisms that maintain network stability. We show that when trained on sequences of characters from text, the network rapidly and effectively self-organizes to learn a latent space mapping of character attributes, similar to word2vec but for characters (i.e. char2vec), forming clusters of vowels, consonants and punctuation for example. It does so with no explicit objective function and no error signal, showing that time-encoded unsupervised SNNs (STUNNs) can maintain dynamical stability while self-organizing to extract complex input relationships using only local learning rules." @default.
- W4385484759 created "2023-08-03" @default.
- W4385484759 creator A5010335338 @default.
- W4385484759 creator A5045046523 @default.
- W4385484759 creator A5091012593 @default.
- W4385484759 date "2023-06-18" @default.
- W4385484759 modified "2023-09-26" @default.
- W4385484759 title "Unsupervised Feature Vector Clustering Using Temporally Coded Spiking Networks" @default.
- W4385484759 cites W1899794420 @default.
- W4385484759 cites W2000066332 @default.
- W4385484759 cites W2066563704 @default.
- W4385484759 cites W2116216716 @default.
- W4385484759 cites W2116356678 @default.
- W4385484759 cites W2130589631 @default.
- W4385484759 cites W2145889472 @default.
- W4385484759 cites W2187011629 @default.
- W4385484759 cites W2798878556 @default.
- W4385484759 cites W2905749112 @default.
- W4385484759 cites W2919115771 @default.
- W4385484759 cites W2951559648 @default.
- W4385484759 cites W2974275398 @default.
- W4385484759 cites W2979359324 @default.
- W4385484759 cites W2984844508 @default.
- W4385484759 cites W2990793844 @default.
- W4385484759 cites W3139657805 @default.
- W4385484759 cites W3147709328 @default.
- W4385484759 cites W3183719272 @default.
- W4385484759 cites W65738273 @default.
- W4385484759 doi "https://doi.org/10.1109/ijcnn54540.2023.10191150" @default.
- W4385484759 hasPublicationYear "2023" @default.
- W4385484759 type Work @default.
- W4385484759 citedByCount "1" @default.
- W4385484759 countsByYear W43854847592023 @default.
- W4385484759 crossrefType "proceedings-article" @default.
- W4385484759 hasAuthorship W4385484759A5010335338 @default.
- W4385484759 hasAuthorship W4385484759A5045046523 @default.
- W4385484759 hasAuthorship W4385484759A5091012593 @default.
- W4385484759 hasConcept C105795698 @default.
- W4385484759 hasConcept C115903868 @default.
- W4385484759 hasConcept C11731999 @default.
- W4385484759 hasConcept C119857082 @default.
- W4385484759 hasConcept C120822770 @default.
- W4385484759 hasConcept C153180895 @default.
- W4385484759 hasConcept C154945302 @default.
- W4385484759 hasConcept C179518139 @default.
- W4385484759 hasConcept C2781390188 @default.
- W4385484759 hasConcept C33923547 @default.
- W4385484759 hasConcept C41008148 @default.
- W4385484759 hasConcept C50644808 @default.
- W4385484759 hasConcept C59404180 @default.
- W4385484759 hasConcept C73555534 @default.
- W4385484759 hasConcept C77637269 @default.
- W4385484759 hasConcept C8038995 @default.
- W4385484759 hasConcept C83665646 @default.
- W4385484759 hasConceptScore W4385484759C105795698 @default.
- W4385484759 hasConceptScore W4385484759C115903868 @default.
- W4385484759 hasConceptScore W4385484759C11731999 @default.
- W4385484759 hasConceptScore W4385484759C119857082 @default.
- W4385484759 hasConceptScore W4385484759C120822770 @default.
- W4385484759 hasConceptScore W4385484759C153180895 @default.
- W4385484759 hasConceptScore W4385484759C154945302 @default.
- W4385484759 hasConceptScore W4385484759C179518139 @default.
- W4385484759 hasConceptScore W4385484759C2781390188 @default.
- W4385484759 hasConceptScore W4385484759C33923547 @default.
- W4385484759 hasConceptScore W4385484759C41008148 @default.
- W4385484759 hasConceptScore W4385484759C50644808 @default.
- W4385484759 hasConceptScore W4385484759C59404180 @default.
- W4385484759 hasConceptScore W4385484759C73555534 @default.
- W4385484759 hasConceptScore W4385484759C77637269 @default.
- W4385484759 hasConceptScore W4385484759C8038995 @default.
- W4385484759 hasConceptScore W4385484759C83665646 @default.
- W4385484759 hasLocation W43854847591 @default.
- W4385484759 hasOpenAccess W4385484759 @default.
- W4385484759 hasPrimaryLocation W43854847591 @default.
- W4385484759 hasRelatedWork W143741948 @default.
- W4385484759 hasRelatedWork W2218369717 @default.
- W4385484759 hasRelatedWork W2292254049 @default.
- W4385484759 hasRelatedWork W2556793986 @default.
- W4385484759 hasRelatedWork W2592385986 @default.
- W4385484759 hasRelatedWork W2773500201 @default.
- W4385484759 hasRelatedWork W3196155444 @default.
- W4385484759 hasRelatedWork W4237551280 @default.
- W4385484759 hasRelatedWork W4245239624 @default.
- W4385484759 hasRelatedWork W4385484759 @default.
- W4385484759 isParatext "false" @default.
- W4385484759 isRetracted "false" @default.
- W4385484759 workType "article" @default.