Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Moraitis, Timoleon"'
Autor:
Weilenmann, Christoph, Ziogas, Alexandros, Zellweger, Till, Portner, Kevin, Mladenović, Marko, Kaniselvan, Manasa, Moraitis, Timoleon, Luisier, Mathieu, Emboras, Alexandros
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 meta-plas
Externí odkaz:
http://arxiv.org/abs/2402.16628
Publikováno v:
Advances in Neural Information Processing Systems, 35, 4543-4557 (2022)
Self-supervised learning (SSL) methods aim to exploit the abundance of unlabelled data for machine learning (ML), however the underlying principles are often method-specific. An SSL framework derived from biological first principles of embodied learn
Externí odkaz:
http://arxiv.org/abs/2210.09224
Publikováno v:
The Eleventh International Conference on Learning Representations (2023) Retrieved from https://openreview.net/forum?id=8gd4M-_Rj1
Recent approximations to backpropagation (BP) have mitigated many of BP's computational inefficiencies and incompatibilities with biology, but important limitations still remain. Moreover, the approximations significantly decrease accuracy in benchma
Externí odkaz:
http://arxiv.org/abs/2209.11883
Publikováno v:
Proceedings of the 39th International Conference on Machine Learning, 162:18704-18722 (2022)
Short-term plasticity (STP) is a mechanism that stores decaying memories in synapses of the cerebral cortex. In computing practice, STP has been used, but mostly in the niche of spiking neurons, even though theory predicts that it is the optimal solu
Externí odkaz:
http://arxiv.org/abs/2206.14048
Publikováno v:
International Conference on Learning Representations. https://openreview.net/forum?id=iMH1e5k7n3L (2022)
Biological spiking neural networks (SNNs) can temporally encode information in their outputs, e.g. in the rank order in which neurons fire, whereas artificial neural networks (ANNs) conventionally do not. As a result, models of SNNs for neuromorphic
Externí odkaz:
http://arxiv.org/abs/2110.02865
Publikováno v:
Neuromorphic Computing and Engineering, 2(4), 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:
http://arxiv.org/abs/2107.05747
Neural processing on devices and circuits is fast becoming a popular approach to emulate biological neural networks. Elaborate CMOS and memristive technologies have been employed to achieve this, including chalcogenide-based in-memory computing conce
Externí odkaz:
http://arxiv.org/abs/2107.00915
Autor:
Sarwat, Syed Ghazi, Kersting, Benedikt, Moraitis, Timoleon, Jonnalagadda, Vara Prasad, Sebastian, Abu
In the mammalian nervous system, various synaptic plasticity rules act, either individually or synergistically, and over wide-ranging timescales to dictate the processes that enable learning and memory formation. To mimic biological cognition for art
Externí odkaz:
http://arxiv.org/abs/2105.13861
Biological neurons and their in-silico emulations for neuromorphic artificial intelligence (AI) use extraordinarily energy-efficient mechanisms, such as spike-based communication and local synaptic plasticity. It remains unclear whether these neurona
Externí odkaz:
http://arxiv.org/abs/2009.06808
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:
http://arxiv.org/abs/2004.03953