Zobrazeno 1 - 10
of 503
pro vyhledávání: '"brain‐inspired computing"'
Publikováno v:
Frontiers in Neuroscience, Vol 18 (2024)
Externí odkaz:
https://doaj.org/article/410c8c722c734a45880a01e5c7948917
Autor:
Olivier Maher, Roy Bernini, Nele Harnack, Bernd Gotsmann, Marilyne Sousa, Valeria Bragaglia, Siegfried Karg
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-15 (2024)
Abstract With remarkable electrical and optical switching properties induced at low power and near room temperature (68 °C), vanadium dioxide (VO2) has sparked rising interest in unconventional computing among the phase-change materials research com
Externí odkaz:
https://doaj.org/article/2446e7a23d2e4a4dbbf06c4572eb28ae
Autor:
Alexandre Bittar, Philip N. Garner
Publikováno v:
Frontiers in Neuroscience, Vol 18 (2024)
Understanding cognitive processes in the brain demands sophisticated models capable of replicating neural dynamics at large scales. We present a physiologically inspired speech recognition architecture, compatible and scalable with deep learning fram
Externí odkaz:
https://doaj.org/article/e05d8260d3284aaaafc1e4ee3897ddde
Autor:
Yang Ni, Danny Abraham, Mariam Issa, Alejandro Hernandez-Cano, Mahdi Imani, Pietro Mercati, Mohsen Imani
Publikováno v:
IEEE Access, Vol 12, Pp 138519-138534 (2024)
In wireless networks, dynamic spectrum access is the key to improving spectrum utilization and increasing channel capacity. Since the channels in wireless networks are highly correlated, they require intelligent algorithms to dynamically handle multi
Externí odkaz:
https://doaj.org/article/bb86c719e18a488da0555f4e75b2d5b3
Publikováno v:
Frontiers in Neuroscience, Vol 18 (2024)
In neural circuits, recurrent connectivity plays a crucial role in network function and stability. However, existing recurrent spiking neural networks (RSNNs) are often constructed by random connections without optimization. While RSNNs can produce r
Externí odkaz:
https://doaj.org/article/f5583e66573c43748f377089b5acb982
Publikováno v:
Frontiers in Nanotechnology, Vol 6 (2024)
Nanoparticles interconnected by insulating organic molecules exhibit nonlinear switching behavior at low temperatures. By assembling these switches into a network and manipulating charge transport dynamics through surrounding electrodes, the network
Externí odkaz:
https://doaj.org/article/470e7f76f53840ee9e014b01ff55d508
Publikováno v:
Frontiers in Artificial Intelligence, Vol 7 (2024)
IntroductionBrain-inspired computing has become an emerging field, where a growing number of works focus on developing algorithms that bring machine learning closer to human brains at the functional level. As one of the promising directions, Hyperdim
Externí odkaz:
https://doaj.org/article/b2aa1d82f67f4e07bf103c95c286d70c
Autor:
Liu Hao, Chai Hongfeng
Publikováno v:
中国工程科学, Vol 25, Iss 6, Pp 61-79 (2023)
Spiking neural network (SNN) is a new generation of artificial neural network. It is more biologically plausible and has been widely concerned by scholars owing to its unique information coding schemes, rich spatiotemporal dynamics, and event-driven
Externí odkaz:
https://doaj.org/article/2cee47836c544fae80de33273076f7a6
Publikováno v:
Complex & Intelligent Systems, Vol 10, Iss 2, Pp 1937-1952 (2023)
Abstract Spiking Neural Network (SNN) is one of the mainstream frameworks for brain-like computing and neuromorphic computing, which has the potential to overcome current AI challenges, for example, low-power learning dynamic processes. However, ther
Externí odkaz:
https://doaj.org/article/8ccb96779f1f4cdb827c0227d149c930
Publikováno v:
Biomimetics, Vol 9, Iss 6, p 315 (2024)
The traditional Model-Based Reinforcement Learning (MBRL) algorithm has high computational cost, poor convergence, and poor performance in robot spatial cognition and navigation tasks, and it cannot fully explain the ability of animals to quickly ada
Externí odkaz:
https://doaj.org/article/715f8ec6d0574fa2a7bacd7cd1049e14