Optimisation Challenge for a Superconducting Adiabatic Neural Network That Implements XOR and OR Boolean Functions-Reference-Cited by-同舟云学术

Optimisation Challenge for a Superconducting Adiabatic Neural Network That Implements XOR and OR Boolean Functions

Published:2024-05-14 Issue:10 Volume:14 Page:854
ISSN:2079-4991
Container-title:Nanomaterials
language:en
Short-container-title:Nanomaterials

Author:

Pashin Dmitrii S.¹^ORCID,Bastrakova Marina V.¹²^ORCID,Rybin Dmitrii A.¹^ORCID,Soloviev Igor. I.²³⁴^ORCID,Klenov Nikolay V.⁴⁵^ORCID,Schegolev Andrey E.³⁶^ORCID

Affiliation:

1. Faculty of Physics, Lobachevsky State University of Nizhni Novgorod, 603022 Nizhny Novgorod, Russia

2. Russian Quantum Centre, 143025 Moscow, Russia

3. Skobeltsyn Institute of Nuclear Physics, Lomonosov Moscow State University, 119991 Moscow, Russia

4. National University of Science and Technology MISIS, 119049 Moscow, Russia

5. Faculty of Physics, Lomonosov Moscow State University, 119991 Moscow, Russia

6. Science Department, Moscow Technical University of Communication and Informatics (MTUCI), 111024 Moscow, Russia

Abstract

In this article, we consider designs of simple analog artificial neural networks based on adiabatic Josephson cells with a sigmoid activation function. A new approach based on the gradient descent method is developed to adjust the circuit parameters, allowing efficient signal transmission between the network layers. The proposed solution is demonstrated on the example of a system that implements XOR and OR logical operations.

Funder

Strategic Academic Leadership Program “Priority-2030”

Russian Science Foundation

Foundation for the Advancement of Theoretical Physics and Mathematics “BASIS”

Rosatom in the framework of the Roadmap for Quantum computing

Publisher

MDPI AG

Link

https://www.mdpi.com/2079-4991/14/10/854/pdf

Reference67 articles.

1. Stereo matching by training a convolutional neural network to compare image patches;Zbontar;J. Mach. Learn. Res.,2016

2. Exploring recurrent neural networks for on-line handwritten signature biometrics;Tolosana;IEEE Access,2018

3. Kaya, M., and Bilge, H.Ş. (2019). Deep metric learning: A survey. Symmetry, 11.

4. Off-line handwritten signature verification using compositional synthetic generation of signatures and Siamese Neural Networks;Ruiz;Neurocomputing,2020

5. Deep face recognition: A survey;Wang;Neurocomputing,2021

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. SuperSIM: a comprehensive benchmarking framework for neural networks using superconductor Josephson devices;Superconductor Science and Technology;2024-08-22