EPOC: A 28-nm 5.3 pJ/SOP Event-driven Parallel Neuromorphic Hardware with Neuromodulation-based Online Learning.

Faquan Chen, Qingyang Tian, Lisheng Xie, Yifan Zhou, Ziren Wu, Liangshun Wu, Rendong Ying, Fei Wen, Peilin Liu
{"title":"EPOC: A 28-nm 5.3 pJ/SOP Event-driven Parallel Neuromorphic Hardware with Neuromodulation-based Online Learning.","authors":"Faquan Chen, Qingyang Tian, Lisheng Xie, Yifan Zhou, Ziren Wu, Liangshun Wu, Rendong Ying, Fei Wen, Peilin Liu","doi":"10.1109/TBCAS.2024.3470520","DOIUrl":null,"url":null,"abstract":"<p><p>Bio-inspired neuromorphic hardware with learning ability is highly promising to achieve human-like intelligence, particularly in terms of high energy efficiency and strong environmental adaptability. Though many customized prototypes have demonstrated learning ability, learning on neuromorphic hardware still lacks a bio-plausible and unified learning framework, and inherent spike-based sparsity and parallelism have not been fully exploited, which fundamentally limits their computational efficiency and scale. Therefore, we develop a unified, event-driven, and massively parallel multi-core neuromorphic online learning processor, namely EPOC. We present a neuromodulation-based neuromorphic online learning framework to unify various learning algorithms, and EPOC supports high-accuracy local/global supervised Spike Neural Network (SNN) learning with a low-memory-demand streaming single-sample learning strategy through different neuromodulator formulations. EPOC leverages a novel event-driven computation method that fully exploits spike-based sparsity throughout the forward-backward learning phases, and parallel multi-channel and multi-core computing architecture, bringing 9.9× time efficiency improvement compared with the baseline architecture. We synthesize EPOC in a 28-nm CMOS process and perform extensive benchmarking. EPOC achieves state-of-the-art learning accuracy of 99.2%, 98.2%, and 94.3% on the MNIST, NMNIST, and DVS-Gesture benchmarks, respectively. Local-learning EPOC achieves 2.9× time efficiency improvement compared with the global learning counterpart. EPOC operates at a typical clock frequency of 100 MHz, providing a peak 328 GOPS/51 GSOPS throughput and a 5.3 pJ/SOP energy efficiency.</p>","PeriodicalId":94031,"journal":{"name":"IEEE transactions on biomedical circuits and systems","volume":"PP ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on biomedical circuits and systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TBCAS.2024.3470520","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Bio-inspired neuromorphic hardware with learning ability is highly promising to achieve human-like intelligence, particularly in terms of high energy efficiency and strong environmental adaptability. Though many customized prototypes have demonstrated learning ability, learning on neuromorphic hardware still lacks a bio-plausible and unified learning framework, and inherent spike-based sparsity and parallelism have not been fully exploited, which fundamentally limits their computational efficiency and scale. Therefore, we develop a unified, event-driven, and massively parallel multi-core neuromorphic online learning processor, namely EPOC. We present a neuromodulation-based neuromorphic online learning framework to unify various learning algorithms, and EPOC supports high-accuracy local/global supervised Spike Neural Network (SNN) learning with a low-memory-demand streaming single-sample learning strategy through different neuromodulator formulations. EPOC leverages a novel event-driven computation method that fully exploits spike-based sparsity throughout the forward-backward learning phases, and parallel multi-channel and multi-core computing architecture, bringing 9.9× time efficiency improvement compared with the baseline architecture. We synthesize EPOC in a 28-nm CMOS process and perform extensive benchmarking. EPOC achieves state-of-the-art learning accuracy of 99.2%, 98.2%, and 94.3% on the MNIST, NMNIST, and DVS-Gesture benchmarks, respectively. Local-learning EPOC achieves 2.9× time efficiency improvement compared with the global learning counterpart. EPOC operates at a typical clock frequency of 100 MHz, providing a peak 328 GOPS/51 GSOPS throughput and a 5.3 pJ/SOP energy efficiency.

EPOC:基于神经调制在线学习的 28 纳米 5.3 pJ/SOP 事件驱动并行神经形态硬件。
具有学习能力的生物启发神经形态硬件很有希望实现类人智能,特别是在高能效和强环境适应性方面。虽然许多定制的原型已经展示了学习能力,但神经形态硬件的学习仍然缺乏一个生物可信的统一学习框架,基于尖峰的固有稀疏性和并行性也没有得到充分利用,这从根本上限制了其计算效率和规模。因此,我们开发了一种统一、事件驱动和大规模并行的多核神经形态在线学习处理器,即 EPOC。我们提出了一个基于神经调制的神经形态在线学习框架来统一各种学习算法,EPOC通过不同的神经调制器形式,以低内存需求的流式单样本学习策略支持高精度的局部/全局监督穗状神经网络(SNN)学习。EPOC 采用新颖的事件驱动计算方法,在整个前向-后向学习阶段充分利用基于尖峰的稀疏性,并采用并行多通道和多核计算架构,与基线架构相比,时间效率提高了 9.9 倍。我们在 28 纳米 CMOS 工艺中合成了 EPOC,并进行了广泛的基准测试。在 MNIST、NMNIST 和 DVS-Gesture 基准测试中,EPOC 的学习准确率分别达到了 99.2%、98.2% 和 94.3% 的一流水平。与全局学习相比,本地学习 EPOC 的时间效率提高了 2.9 倍。EPOC 的典型时钟频率为 100 MHz,峰值吞吐量为 328 GOPS/51 GSOPS,能效为 5.3 pJ/SOP。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信