Superconductor Computing for Neural Networks

Ishida, Koki; Byun, Ilkwon; Nagaoka, Ikki; Fukumitsu, Kosuke; Tanaka, Masamitsu; Kawakami, Satoshi; Tanimoto, Teruo; Ono, Takatsugu; Kim, Jangwoo; Inoue, Katsuro

doi:10.1109/mm.2021.3070488

Cited by 27 publications

(18 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When using ASL schemes, the functioning of the ANN is based on handling the information given not in the form of the presence or absence of a quant, but as the magnitude and direction of circulating superconducting currents. The performance of the hardware implementation of a superconducting neural processor while executing the test on examples of standard configurations of neural networks exceeds the performance of a semiconductor analog (TPU) by 23 times on average [1]. These indicators were demonstrated when using memory with a bandwidth (300 GB/s) and a typical clock frequency of a superconducting processor (52.6 GHz) [1].…”

Section: Introductionmentioning

confidence: 99%

“…Theoretical and practical research of artificial intelligence systems, methods of machine learning, and artificial neural networks are being actively developed in recent years [1,2]. The main goal of artificial neural networks is to effectively use the features of the human brain such as the learning ability, the ability to model complex separating surfaces in a multidimensional feature space, distributed memory in order to solve computational problems.…”

Section: Introductionmentioning

confidence: 99%

“…The limitations imposed by the dissipative nature of CMOS technology make the hardware acceleration of both large convolutional neural networks of deep learning and the increasingly popular transformer networks extremely difficult to implement [5]. On the other hand, an alternative and actively developing approach for the implementation of artificial neural networks (ANN) is the development of energy-efficient superconducting solutions [1,[7][8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

“…The performance of the hardware implementation of a superconducting neural processor while executing the test on examples of standard configurations of neural networks exceeds the performance of a semiconductor analog (TPU) by 23 times on average [1]. These indicators were demonstrated when using memory with a bandwidth (300 GB/s) and a typical clock frequency of a superconducting processor (52.6 GHz) [1]. A number of examples per learning iteration was set according to the capacity of the on-chip memory, which made it possible to avoid addressing the external memory inside the loop.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Dynamic Processes in a Superconducting Adiabatic Neuron with Non-Shunted Josephson Contacts

et al. 2021

View full text Add to dashboard Cite

We investigated the dynamic processes in a superconducting neuron based on Josephson contacts without resistive shunting (SC-neuron). Such a cell is a key element of perceptron-type neural networks that operate in both classical and quantum modes. The analysis of the obtained results allowed us to find the mode when the transfer characteristic of the element implements the “sigmoid” activation function. The numerical approach to the analysis of the equations of motion and the Monte Carlo method revealed the influence of inertia (capacitances), dissipation, and temperature on the dynamic characteristics of the neuron.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Dynamic Processes in a Superconducting Adiabatic Neuron with Non-Shunted Josephson Contacts

et al. 2021

View full text Add to dashboard Cite

show abstract

“…13,15 Generation and manipulation of JVs [16][17][18][19] is a basis of many applications of superconducting technology. This includes quantum computing based on flux 20,21 and JV 8,22,23 qubits, control of quantum circuits, [24][25][26] novel superconducting neural networks with information encoded in the magnetic flux, [27][28][29] reservoir computing based on superconducting electronics, 30 superconducting digital and mixed-signal circuits, 31-35 cryogenic memory. [36][37][38][39] One of the advantages of superconducting de-vices is related to their low power dissipation.…”

Section: Introductionmentioning

confidence: 99%

Revealing Josephson vortex dynamics in proximity junctions below critical current

Stolyarov,

Ruzhitskiy,

Hovhannisyan

et al. 2022

Preprint

View full text Add to dashboard Cite

Made of a thin non-superconducting metal (N) sandwiched by two superconductors (S), SNS Josephson junctions enable novel quantum functionalities by mixing up the intrinsic electronic properties of N with the superconducting correlations induced from S by proximity. Electronic properties of these devices are governed by Andreev quasiparticles 1 which are absent in conventional SIS junctions whose insulating barrier (I) between the two S electrodes owns no electronic states. Here we focus on the Josephson vortex (JV) motion inside Nb-Cu-Nb proximity junctions subject to electric currents and magnetic fields. The results of local (Magnetic Force Microscopy) and global (transport) experiments provided simultaneously are compared with our numerical model, revealing the existence of several distinct dynamic regimes of the JV motion. One of them, identified as a fast hysteretic entry/escape below the critical value of Josephson current, is analyzed and suggested for low-dissipative logic and memory elements.

show abstract

Reconfigurable Neuromorphic Computing: Materials, Devices, and Integration

Chen

Guo

et al. 2023

Advanced Materials

View full text Add to dashboard Cite

Neuromorphic computing has been attracting ever‐increasing attention due to superior energy efficiency, with great promise to promote the next wave of artificial general intelligence in the post‐Moore era. Current approaches are, however, broadly designed for stationary and unitary assignments, thus encountering reluctant interconnections, power consumption, and data‐intensive computing in that domain. Reconfigurable neuromorphic computing, an on‐demand paradigm inspired by the inherent programmability of brain, can maximally reallocate finite resources to perform the proliferation of reproducibly brain‐inspired functions, highlighting a disruptive framework for bridging the gap between different primitives. Although relevant research has flourished in diverse materials and devices with novel mechanisms and architectures, a precise overview remains blank and urgently desirable. Herein, the recent strides along this pursuit are systematically reviewed from material, device, and integration perspectives. At the material and device level, we comprehensively conclude the dominant mechanisms for reconfigurability, categorized into ion migration, carrier migration, phase transition, spintronics, and photonics. Integration‐level developments for reconfigurable neuromorphic computing are also exhibited. Finally, a perspective on the future challenges for reconfigurable neuromorphic computing is discussed, definitely expanding its horizon for scientific communities.This article is protected by copyright. All rights reserved

show abstract

Superconductor Computing for Neural Networks

Cited by 27 publications

References 9 publications

Dynamic Processes in a Superconducting Adiabatic Neuron with Non-Shunted Josephson Contacts

Dynamic Processes in a Superconducting Adiabatic Neuron with Non-Shunted Josephson Contacts

Revealing Josephson vortex dynamics in proximity junctions below critical current

Reconfigurable Neuromorphic Computing: Materials, Devices, and Integration

Contact Info

Product

Resources

About