A design methodology for fault-tolerant computing using astrocyte neural networks

A design methodology for fault-tolerant computing using astrocyte neural networks
复制标题

使用星形胶质细胞神经网络进行容错计算的设计方法

DOI:
10.1145/3528416.3530232
复制
发表时间:
2022
期刊:
CF '22: Proceedings of the 19th ACM International Conference on Computing Frontiers
影响因子:
--
通讯作者:
Das, Anup
Das, Anup
中科院分区:
--
文献类型:
--
作者:
Isik, Murat;Paul, Ankita;Varshika, M. Lakshmi;Das, Anup

文献摘要

参考文献

被引文献

相似文献

我们提出了一种设计方法来促进深度学习模型的容错。首先,我们实现了一个多核容错神经形态硬件设计,其中每个神经形态核心中的神经元和突触电路都被星形胶质细胞电路包围,星形胶质细胞是大脑的星形胶质细胞,通过使用闭环逆行反馈信号恢复失败神经元的尖峰放电频率来促进自我修复。接下来,我们在深度学习模型中引入星形胶质细胞,以实现对硬件故障所需的容忍度。最后,我们使用一个系统软件分区的星形胶质细胞使能的模型成集群,并实现他们提出的容错神经形态设计。我们使用七种深度学习推理模型来评估这种设计方法,并表明它具有面积和功耗效率。
We propose a design methodology to facilitate fault tolerance of deep learning models. First, we implement a many-core fault-tolerant neuromorphic hardware design, where neuron and synapse circuitries in each neuromorphic core are enclosed with astrocyte circuitries, the star-shaped glial cells of the brain that facilitate self-repair by restoring the spike firing frequency of a failed neuron using a closed-loop retrograde feedback signal. Next, we introduce astrocytes in a deep learning model to achieve the required degree of tolerance to hardware faults. Finally, we use a system software to partition the astrocyte-enabled model into clusters and implement them on the proposed fault-tolerant neuromorphic design. We evaluate this design methodology using seven deep learning inference models and show that it is both area- and power-efficient.
使用非易失性存储器提高神经形态计算的可靠性
DOI: 10.1109/edcc51268.2020.00013
发表时间: 2020
期刊: 2020 16th European Dependable Computing Conference (EDCC
影响因子: --
作者:
Song, Shihao;Das, Anup;Kandasamy, Nagarajan
通讯作者: Kandasamy, Nagarajan
一种位交错嵌入式汉明方案,用于纠正基于 SRAM 的 FPGA 的单位和多位翻转
DOI: --
发表时间: 2014
期刊: International Conference on Field-Programmable Logic and Applications
影响因子: --
作者:
Shyamsundar Venkataraman;Rui Santos;Anup Das;Akash Kumar
通讯作者: Akash Kumar
终身可靠性感知神经形态计算的案例
DOI: 10.1109/mwscas48704.2020.9184557
发表时间: 2020
期刊: 2020 IEEE 63rd International Midwest Symposium on Circuits and Systems (MWSCAS
影响因子: --
作者:
Song, Shihao;Das, Anup
通讯作者: Das, Anup
DOI: 10.1109/isqed51717.2021.9424332
发表时间: 2021-04
期刊: 2021 22nd International Symposium on Quality Electronic Design (ISQED)
影响因子: --
作者:
Geng Yuan;Zhiheng Liao;Xiaolong Ma;Yuxuan Cai;Zhenglun Kong;Xuan Shen;Jingyan Fu;Zhengang Li;Chengming Zhang;Hongwu Peng;Ning Liu;Ao Ren;Jinhui Wang;Yanzhi Wang
通讯作者: Geng Yuan;Zhiheng Liao;Xiaolong Ma;Yuxuan Cai;Zhenglun Kong;Xuan Shen;Jingyan Fu;Zhengang Li;Chengming Zhang;Hongwu Peng;Ning Liu;Ao Ren;Jinhui Wang;Yanzhi Wang
DOI: 10.1109/tbcas.2017.2759700
发表时间: 2018-02-01
影响因子: 5.1
作者:
Moradi, Saber;Qiao, Ning;Indiveri, Giacomo
通讯作者: Indiveri, Giacomo