Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Skalli Anas"'
Autor:
Skalli, Anas, Goldmann, Mirko, Haghighi, Nasibeh, Reitzenstein, Stephan, Lott, James A., Brunner, Daniel
Artificial neural networks (ANNs) represent a fundamentally connectionnist and distributed approach to computing, and as such they differ from classical computers that utilize the von Neumann architecture. This has revived research interest in new un
Externí odkaz:
http://arxiv.org/abs/2409.01042
Autor:
Momeni, Ali, Rahmani, Babak, Scellier, Benjamin, Wright, Logan G., McMahon, Peter L., Wanjura, Clara C., Li, Yuhang, Skalli, Anas, Berloff, Natalia G., Onodera, Tatsuhiro, Oguz, Ilker, Morichetti, Francesco, del Hougne, Philipp, Gallo, Manuel Le, Sebastian, Abu, Mirhoseini, Azalia, Zhang, Cheng, Marković, Danijela, Brunner, Daniel, Moser, Christophe, Gigan, Sylvain, Marquardt, Florian, Ozcan, Aydogan, Grollier, Julie, Liu, Andrea J., Psaltis, Demetri, Alù, Andrea, Fleury, Romain
Physical neural networks (PNNs) are a class of neural-like networks that leverage the properties of physical systems to perform computation. While PNNs are so far a niche research area with small-scale laboratory demonstrations, they are arguably one
Externí odkaz:
http://arxiv.org/abs/2406.03372
Autor:
Skalli Anas, Goldmann Mirko, Porte Xavier, Haghighi Nasibeh, Reitzenstein Stephan, Lott James A., Brunner Daniel
Publikováno v:
EPJ Web of Conferences, Vol 287, p 13008 (2023)
We experimentally demonstrate an autonomous, fully tuneable and scalable neural network of 350+ parallel nodes based on a large area, multimode semiconductor laser. We implement online learning strategies based on reinforcement learning. Our system a
Externí odkaz:
https://doaj.org/article/08c76dfbfdc849f9821e066bcfaf80b3
Publikováno v:
EPJ Web of Conferences, Vol 287, p 13009 (2023)
A high-performance photonic reservoir, which utilizes the injection locking effect in a highly multimodal semiconductor laser, has been developed. This innovative design allows for fully parallel and high-bandwidth operation. The output of this syste
Externí odkaz:
https://doaj.org/article/0a1102fcc7fb443bb9cb4169d61a45da
Publikováno v:
EPJ Web of Conferences, Vol 287, p 13006 (2023)
Photonic neural networks are a highly sought-after area of research due to their potential for high-performance complex computing. Unlike artificial neural networks, which use simple nonlinear maps, biological neurons transmit information and perform
Externí odkaz:
https://doaj.org/article/b450209327544b33b21ec47a98f3c5da
Autor:
Skalli, Anas, Porte, Xavier, Haghighi, Nasibeh, Reitzenstein, Stephan, Lott, James A., Brunner, D.
Artificial neural networks have become a staple computing technique in many fields. Yet, they present fundamental differences with classical computing hardware in the way they process information. Photonic implementations of neural network architectu
Externí odkaz:
http://arxiv.org/abs/2112.08947
Autor:
Skalli, Anas, Robertson, Joshua, Owen-Newns, Dafydd, Hejda, Matej, Porte, Xavier, Reitzenstein, Stephan, Hurtado, Antonio, Brunner, D.
Photonic realizations of neural network computing hardware are a promising approach to enable future scalability of neuromorphic computing. In this review we provide an overview on vertical-cavity surface-emitting lasers (VCSELs) and how these high-p
Externí odkaz:
http://arxiv.org/abs/2112.08086
Autor:
Porte, Xavier, Skalli, Anas, Haghighi, Nasibeh, Reitzenstein, Stephan, Lott, James A., Brunner, Daniel
Neural networks are one of the disruptive computing concepts of our time. However, they fundamentally differ from classical, algorithmic computing in a number of fundamental aspects. These differences result in equally fundamental, severe and relevan
Externí odkaz:
http://arxiv.org/abs/2012.11153
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.