Zobrazeno 1 - 10
of 122
pro vyhledávání: '"Van Vaerenbergh Thomas"'
Multiplexing in photonics as a resource for optical ternary content-addressable memory functionality
Autor:
London Yanir, Van Vaerenbergh Thomas, Ramini Luca, Descos Antoine, Buonanno Luca, Youn Jinsung, Li Can, Graves Catherine E., Fiorentino Marco, Beausoleil Raymond G.
Publikováno v:
Nanophotonics, Vol 12, Iss 22, Pp 4137-4155 (2023)
In this paper, we combine a Content-Addressable Memory (CAM) encoding scheme previously proposed for analog electronic CAMs (E-CAMs) with optical multiplexing techniques to create two new photonic CAM architectures—wavelength-division multiplexing
Externí odkaz:
https://doaj.org/article/e35bad731e6647f780b6e7b40ba93f8e
Publikováno v:
Nanophotonics, Vol 10, Iss 15, Pp 3843-3856 (2021)
We present a proof-of-concept technique for the inverse design of electromagnetic devices motivated by the policy gradient method in reinforcement learning, named PHORCED (PHotonic Optimization using REINFORCE Criteria for Enhanced Design). This tech
Externí odkaz:
https://doaj.org/article/73c23020fca646c58959e509beee6f4c
Autor:
Zhang, Xiangyi, Rozada, Ignacio, Böhm, Fabian, Valiante, Elisabetta, Noori, Moslem, Van Vaerenbergh, Thomas, Yang, Chan-Woo, Pedretti, Giacomo, Mohseni, Masoud, Beausoleil, Raymond
In-memory computing (IMC) has been shown to be a promising approach for solving binary optimization problems while significantly reducing energy and latency. Building on the advantages of parallel computation, we propose an IMC-compatible parallelism
Externí odkaz:
http://arxiv.org/abs/2409.09152
Autor:
Peng, Yiwei, Hooten, Sean, Yu, Xinling, Van Vaerenbergh, Thomas, Yuan, Yuan, Xiao, Xian, Tossoun, Bassem, Cheung, Stanley, Fiorentino, Marco, Beausoleil, Raymond
Kolmogorov-Arnold Networks (KAN) models were recently proposed and claimed to provide improved parameter scaling and interpretability compared to conventional multilayer perceptron (MLP) models. Inspired by the KAN architecture, we propose the Photon
Externí odkaz:
http://arxiv.org/abs/2408.08407
Autor:
Yu, Xinling, Hooten, Sean, Liu, Ziyue, Zhao, Yequan, Fiorentino, Marco, Van Vaerenbergh, Thomas, Zhang, Zheng
Operator learning has become a powerful tool in machine learning for modeling complex physical systems governed by partial differential equations (PDEs). Although Deep Operator Networks (DeepONet) show promise, they require extensive data acquisition
Externí odkaz:
http://arxiv.org/abs/2407.11253
Autor:
Hejda, Matěj, Marchesin, Federico, Papadimitriou, George, Gizopoulos, Dimitris, Charbonnier, Benoit, Orobtchouk, Régis, Bienstman, Peter, Van Vaerenbergh, Thomas, Pavanello, Fabio
In this work, we discuss our vision for neuromorphic accelerators based on integrated photonics within the framework of the Horizon Europe NEUROPULS project. Augmented integrated photonic architectures that leverage phase-change and III-V materials f
Externí odkaz:
http://arxiv.org/abs/2407.06240
Autor:
Hooten, Sean, Sun, Peng, Gantz, Liron, Fiorentino, Marco, Beausoleil, Raymond G., Van Vaerenbergh, Thomas
Shape optimization approaches to inverse design offer low-dimensional, physically-guided parameterizations of structures by representing them as combinations of shape primitives. However, on discretized rectilinear simulation grids, computing the gra
Externí odkaz:
http://arxiv.org/abs/2311.05646
Autor:
Hizzani, Mohammad, Heittmann, Arne, Hutchinson, George, Dobrynin, Dmitrii, Van Vaerenbergh, Thomas, Bhattacharya, Tinish, Renaudineau, Adrien, Strukov, Dmitri, Strachan, John Paul
Publikováno v:
2024 IEEE International Symposium on Circuits and Systems (ISCAS)
Ising solvers offer a promising physics-based approach to tackle the challenging class of combinatorial optimization problems. However, typical solvers operate in a quadratic energy space, having only pair-wise coupling elements which already dominat
Externí odkaz:
http://arxiv.org/abs/2311.01171
Autor:
Pavanello, Fabio, Marchand, Cedric, O'Connor, Ian, Orobtchouk, Regis, Mandorlo, Fabien, Letartre, Xavier, Cueff, Sebastien, Vatajelu, Elena Ioana, Di Natale, Giorgio, Cluzel, Benoit, Coillet, Aurelien, Charbonnier, Benoit, Noe, Pierre, Kavan, Frantisek, Zoldak, Martin, Szaj, Michal, Bienstman, Peter, Van Vaerenbergh, Thomas, Ruhrmair, Ulrich, Flores, Paulo, Silva, Luis Guerra e, Chaves, Ricardo, Silveira, Luis-Miguel, Ceccato, Mariano, Gizopoulos, Dimitris, Papadimitriou, George, Karakostas, Vasileios, Brando, Axel, Cazorla, Francisco J., Canal, Ramon, Closas, Pau, Gusi-Amigo, Adria, Crovetti, Paolo, Carpegna, Alessio, Carmona, Tzamn Melendez, Di Carlo, Stefano, Savino, Alessandro
Publikováno v:
IEEE European Test Symposium 2023
This special session paper introduces the Horizon Europe NEUROPULS project, which targets the development of secure and energy-efficient RISC-V interfaced neuromorphic accelerators using augmented silicon photonics technology. Our approach aims to de
Externí odkaz:
http://arxiv.org/abs/2305.03139
Autor:
Pavanello, Fabio, Vatajelu, Elena Ioana, Bosio, Alberto, Van Vaerenbergh, Thomas, Bienstman, Peter, Charbonnier, Benoit, Carpegna, Alessio, Di Carlo, Stefano, Savino, Alessandro
Publikováno v:
2023 IEEE 41st VLSI Test Symposium (VTS)
The field of neuromorphic computing has been rapidly evolving in recent years, with an increasing focus on hardware design and reliability. This special session paper provides an overview of the recent developments in neuromorphic computing, focusing
Externí odkaz:
http://arxiv.org/abs/2305.01818