Presentation 2023-08-08
Design and Implementation of Neuron Circuit Using Adiabatic Quantum-Flux-Parametron Logic
Tomoharu Yamauchi, Hao San, Naoki Takeuchi, Nobuyuki Yoshikawa, Olivia Chen,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Adiabatic quantum-flux-parametron (AQFP) logic is a promising technology for future energy-efficient,high performance information processing systems. It is a low power dissipation circuits in superconducting digital circuits.In this paper,we proposed a binary neural network (BNN) to achieve low power dissipation and small area, and designed and implemented a neuron circuit that introduces analog operations using magnetic coupling-based confluence. To effectively solve the memory problem in neural networks using superconducting integrated circuits. As an operational demonstration, we designed and implemented 4, 8 and 16 input neuron circuits using AIST $mathrm{10,kA/cm^2}$ 4-layer Nb process,and confirmed their operation from low-speed measurements at $mathrm{100,kHz}$.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) adiabatic logic / superconducting digital circuits / AQFP / binary neural network
Paper # SCE2023-11
Date of Issue 2023-08-01 (SCE)

Conference Information
Committee SCE
Conference Date 2023/8/8(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Yokohama National Univ.
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Shigehito Miki(NICT)
Vice Chair
Secretary (Kanazawa Inst. of Tech.)
Assistant Hiroyuki Akaike(Daido Univ.)

Paper Information
Registration To Technical Committee on Superconductive Electronics
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Design and Implementation of Neuron Circuit Using Adiabatic Quantum-Flux-Parametron Logic
Sub Title (in English)
Keyword(1) adiabatic logic
Keyword(2) superconducting digital circuits
Keyword(3) AQFP
Keyword(4) binary neural network
1st Author's Name Tomoharu Yamauchi
1st Author's Affiliation Tokyo City University(Tokyo City Univ.)
2nd Author's Name Hao San
2nd Author's Affiliation Tokyo City University(Tokyo City Univ.)
3rd Author's Name Naoki Takeuchi
3rd Author's Affiliation National Institute of Advanced Industrial Science and Technology/Yokohama National University(AIST/Yokohama National Univ.)
4th Author's Name Nobuyuki Yoshikawa
4th Author's Affiliation Yokohama National University(Yokohama National Univ.)
5th Author's Name Olivia Chen
5th Author's Affiliation Tokyo City University(Tokyo City Univ.)
Date 2023-08-08
Paper # SCE2023-11
Volume (vol) vol.123
Number (no) SCE-153
Page pp.pp.53-57(SCE),
#Pages 5
Date of Issue 2023-08-01 (SCE)