Projects per year
Abstract
Ising machines are a promising non-von-Neumann computational concept for neural network training and combinatorial optimization. However, while various neural networks can be implemented with Ising machines, their inability to perform fast statistical sampling makes them inefficient for training neural networks compared to digital computers. Here, we introduce a universal concept to achieve ultrafast statistical sampling with analog Ising machines by injecting noise. With an opto-electronic Ising machine, we experimentally demonstrate that this can be used for accurate sampling of Boltzmann distributions and for unsupervised training of neural networks, with equal accuracy as software-based training. Through simulations, we find that Ising machines can perform statistical sampling orders-of-magnitudes faster than software-based methods. This enables the use of Ising machines beyond combinatorial optimization and makes them into efficient tools for machine learning and other applications.
Original language | English |
---|---|
Article number | 5847 |
Journal | Nature Communications |
Volume | 13 |
Issue number | 1 |
DOIs | |
Publication status | Published - 4 Oct 2022 |
Bibliographical note
Funding Information:We acknowledge financial support from the Research Foundation Flanders (FWO) under the grants G028618N, G029519N, and G006020N as well as the Hercules Foundation and the Research Council of the Vrije Universiteit Brussel (F.B., G.V., G.V.d.S.). Additional funding was provided by the EOS project “Photonic Ising Machines”. This project (EOS number 40007536) has received funding from the FWO and F.R.S.-FNRS under the Excellence of Science (EOS) program (F.B., G.V., G.V.d.S.).
Publisher Copyright:
© 2022, The Author(s).
Copyright:
Copyright 2022 Elsevier B.V., All rights reserved.
Fingerprint
Dive into the research topics of 'Noise-injected analog Ising machines enable ultrafast statistical sampling and machine learning'. Together they form a unique fingerprint.Projects
- 1 Active
-
FWOEOS20: Photonic Ising Machines
Van Der Sande, G. & Verschaffelt, G.
1/01/22 → 31/12/25
Project: Fundamental