Zobrazeno 1 - 10
of 38
pro vyhledávání: '"Timoleon Moraitis"'
Autor:
Christoph Weilenmann, Alexandros Nikolaos Ziogas, Till Zellweger, Kevin Portner, Marko Mladenović, Manasa Kaniselvan, Timoleon Moraitis, Mathieu Luisier, Alexandros Emboras
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-13 (2024)
Abstract Biological neural networks do not only include long-term memory and weight multiplication capabilities, as commonly assumed in artificial neural networks, but also more complex functions such as short-term memory, short-term plasticity, and
Externí odkaz:
https://doaj.org/article/a24f297471764226825bbfa23e486945
Publikováno v:
Nature Communications, Vol 13, Iss 1, Pp 1-9 (2022)
Some types of machine learning rely on the interaction between multiple signals, which requires new devices for efficient implementation. Here, Sarwat et al demonstrate a memristor that is both optically and electronically active, enabling computatio
Externí odkaz:
https://doaj.org/article/381cb23d21e94245b5c173763a903759
Publikováno v:
Neuromorphic Computing and Engineering, Vol 2, Iss 4, p 044017 (2022)
Hebbian plasticity in winner-take-all (WTA) networks is highly attractive for neuromorphic on-chip learning, owing to its efficient, local, unsupervised, and on-line nature. Moreover, its biological plausibility may help overcome important limitation
Externí odkaz:
https://doaj.org/article/628c3bff1fe949f2bfa2a327c76744a4
Autor:
Irem Boybat, Manuel Le Gallo, S. R. Nandakumar, Timoleon Moraitis, Thomas Parnell, Tomas Tuma, Bipin Rajendran, Yusuf Leblebici, Abu Sebastian, Evangelos Eleftheriou
Publikováno v:
Nature Communications, Vol 9, Iss 1, Pp 1-12 (2018)
Memristive technology is a promising avenue towards realizing efficient non-von Neumann neuromorphic hardware. Boybat et al. proposes a multi-memristive synaptic architecture with a counter-based global arbitration scheme to address challenges associ
Externí odkaz:
https://doaj.org/article/beb0eab547c74bc38fb3bf5a3f89b8e7
Autor:
Timoleon Moraitis, Qinghai Guo, Hector Garcia Rodriguez, Franz Scherr, Adrien Journé, Pontus Stenetorp, Yansong Chua, Dmitry Toichkin
Publikováno v:
Proceedings of the Neuromorphic Materials, Devices, Circuits and Systems.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1f90ce27579e6534a5934e18bc6f405a
https://doi.org/10.29363/nanoge.neumatdecas.2023.049
https://doi.org/10.29363/nanoge.neumatdecas.2023.049
Autor:
Fabio Boi, Timoleon Moraitis, Vito De Feo, Francesco Diotalevi, Chiara Bartolozzi, Giacomo Indiveri, Alessandro Vato
Publikováno v:
Frontiers in Neuroscience, Vol 10 (2016)
Bidirectional brain-machine interfaces (BMIs) establish a two-way direct communication link4 between the brain and the external world. A decoder translates recorded neural activity into motor5 commands and an encoder delivers sensory information coll
Externí odkaz:
https://doaj.org/article/cf925bbd5ee4404ca4ab8d80697a39ab
Autor:
Syed Ghazi Sarwat, Benedikt Kersting, Timoleon Moraitis, Vara Prasad Jonnalagadda, Abu Sebastian
Publikováno v:
Nature Nanotechnology
In the mammalian nervous system, various synaptic plasticity rules act, either individually or synergistically, over wide-ranging timescales to enable learning and memory formation. Hence, in neuromorphic computing platforms, there is a significant n
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c8ad3b93f9a16cebe05a5296648b05e9
https://pubmed.ncbi.nlm.nih.gov/35347271
https://pubmed.ncbi.nlm.nih.gov/35347271
Hebbian plasticity in winner-take-all (WTA) networks is highly attractive for neuromorphic on-chip learning, owing to its efficient, local, unsupervised, and on-line nature. Moreover, its biological plausibility may help overcome important limitation
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::109b788bf87f669b4f2f60297f66c25c
Publikováno v:
Scopus-Elsevier
ISCAS
ISCAS
In this paper, we propose a system for file classification in large data sets based on spiking neural networks (SNNs). File information contained in key-value metadata pairs is mapped by a novel correlative temporal encoding scheme to spike patterns
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::acc44c6e8c8b4df09ece3b67a81687b4
http://arxiv.org/abs/2004.03953
http://arxiv.org/abs/2004.03953
Publikováno v:
IEEE Nanotechnology Magazine. 12:45-53
Neural networks (NNs) have been able to provide record-breaking performance in several machine-learning tasks, such as image and speech recognition, natural-language processing, playing complex games, and data analytics for scientific or business pur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2fb9600c7cb600685e8d94384627c1a6
https://doi.org/10.1109/mnano.2018.2845479
https://doi.org/10.1109/mnano.2018.2845479