Time-Domain Digital-to-Analog Converter for Spiking Neural Network Hardware

Author:

Uenohara SeijiORCID,Aihara Kazuyuki

Abstract

AbstractWe propose a new digital-to-analog converter (DAC) for realizing a synapse circuit in mixed-signal spiking neural networks. We refer to this circuit as a “time-domain DAC (TDAC)”. It produces weights for converting a digital input code into voltage using one current waveform. Therefore, the TDAC is more compact than a conventional DAC consisting of many current sources and resistors. Moreover, a TDAC with leak resistance reproduces biologically plausible synaptic responses expressed as alpha functions or dual exponential equations. We also present numerical analysis results for a TDAC and circuit simulation results for a circuit designed using the TSMC 40 nm CMOS process.

Publisher

Springer Science and Business Media LLC

Subject

Applied Mathematics,Signal Processing

Cited by 4 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. A 16-bit DPT-DAC over 120dBc SFDR with Signal-Phase regulation and Switching-Glitch neutralization;AEU - International Journal of Electronics and Communications;2024-03

2. Binary Synaptic Array for Inference and Training with Built-in RRAM Electroforming Circuit;2023 24th International Symposium on Quality Electronic Design (ISQED);2023-04-05

3. Circuit Design and Analysis of Smoothed $${l}_0$$ Norm Approximation for Sparse Signal Reconstruction;Circuits, Systems, and Signal Processing;2022-10-25

4. A Trainable Synapse Circuit Using a Time-Domain Digital-to-Analog Converter;Circuits, Systems, and Signal Processing;2022-09-16

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3