Competitive Hyperparameter Balancing on Spiking Neural Network for a Fast, Accurate and Energy-Efficient Inference

Cited 1 time in webofscience Cited 0 time in scopus
  • Hit : 305
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorKim, Jeonghoko
dc.contributor.authorKim, Dae-Shikko
dc.date.accessioned2018-07-24T01:49:30Z-
dc.date.available2018-07-24T01:49:30Z-
dc.date.created2018-07-02-
dc.date.created2018-07-02-
dc.date.created2018-07-02-
dc.date.created2018-07-02-
dc.date.issued2018-06-27-
dc.identifier.citation15th International Symposium on Neural Networks (ISNN) 2018, pp.44 - 53-
dc.identifier.urihttp://hdl.handle.net/10203/243822-
dc.description.abstractThe Spiking Neural Network (SNN) is currently considered as a next generation neural network model. However, its performance often lags that of classical Artificial Neural Networks. Although there has been a wide range of research to improve the accuracy of SNNs, their performance is determined not only by accuracy, but also by speed and energy efficiency. In this study, we analyzed the relationship between hyperparameters, accuracy, speed and energy of SNN, set a new criterion to estimate the comprehensive performance and applied the Neuroevolutionary algorithm to balance the hyperparameters without the need for manually setting them. The optimized model showed better performance in all terms of our criteria.-
dc.languageEnglish-
dc.publisherInternational Symposium on Neural Networks-
dc.titleCompetitive Hyperparameter Balancing on Spiking Neural Network for a Fast, Accurate and Energy-Efficient Inference-
dc.typeConference-
dc.identifier.wosid000460424800079-
dc.identifier.scopusid2-s2.0-85048035550-
dc.type.rimsCONF-
dc.citation.beginningpage44-
dc.citation.endingpage53-
dc.citation.publicationname15th International Symposium on Neural Networks (ISNN) 2018-
dc.identifier.conferencecountryBY-
dc.identifier.conferencelocationMinsk-
dc.identifier.doi10.1007/978-3-319-92537-0_6-
dc.contributor.localauthorKim, Dae-Shik-
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 1 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0