基于RRAM的低功耗神经突触网络：实时分类的突破

26 浏览量更新于2024-08-28 收藏 770KB PDF 举报

本文主要探讨了"能源高效RRAM（ Resistive Random Access Memory）脉冲神经网络在实时分类中的应用"。RRAM是一种新兴的非易失性存储技术，其电阻可变性使其在构建生物启发的神经形态计算系统中具有巨大的潜力，特别是在能量效率方面。神经形态计算旨在模仿人脑的功能和效率，为包括脑机接口和实时分类在内的众多任务提供有前景的解决方案。 Spiking Neural Networks (SNNs) 是一种模仿生物神经元工作原理的计算模型，它使用脉冲信号（称为"spikes"）来编码和处理信息。这种模型在提升计算系统的性能和能效方面显示出巨大潜力。然而，实际应用中存在两个关键挑战：一是如何实现能耗高效的硬件实现，二是如何有效地训练这种模型，以便它们能够适应复杂的任务并达到高性能。本文作者Yu Wang、Tianqi Tang等人，来自清华大学、匹兹堡大学和加利福尼亚大学圣巴巴拉分校的研究团队，关注的是解决这两个问题。他们提出了一种新型的能源高效RRAM Spiking Neural Network架构，旨在优化能量消耗的同时，提高实时分类任务的处理能力。他们可能采用了先进的RRAM技术，如低功耗的突触模拟，以及针对SNN特性的训练算法，例如基于生物学习规则的强化学习或自组织学习策略。他们的工作可能包括对RRAM单元的精确控制，以模拟神经元的兴奋和抑制过程，以及设计能有效处理和传播spike信号的电路结构。此外，文章可能会讨论如何通过优化网络结构和算法，减少不必要的计算和通信，从而在保持准确性的同时显著降低能耗。这篇研究论文聚焦于通过结合能源高效的RRAM技术和SNN的优势，开发出一种适用于实时分类任务的新型神经形态计算平台。它不仅关注理论上的创新，还可能涉及到实际硬件设计与实验验证，对于推动神经网络在能源受限设备上的实际应用具有重要意义。

Energy Efﬁcient RRAM Spiking Neural Network for

Real Time Classiﬁcation

Yu Wang

, Tianqi Tang

, Lixue Xia

, Boxun Li

, Peng Gu

, Hai Li

, Yuan Xie

, Huazhong Yang

Dept. of E.E., Tsinghua National Laboratory for Information Science and Technology (TNList),

Centre for Brain Inspired Computing Research (CBICR), Tsinghua University, Beijing, China

Dept. of E.C.E., University of Pittsburgh, Pittsburgh, USA

Dept. of E.C.E., University of Califor nia at Santa Barbara, Califor nia, USA

e-mail: yu-wang@mail.tsinghua.edu.cn

ABSTRACT

Inspired by the human brain’s function and eﬃciency, neuro-

morphic computing oﬀers a promising solution for a wide set

of tasks, ranging from brain machine interfaces to real-time

classiﬁcation. The spiking neural network (SNN), which en-

codes and processes information with bionic spikes, is an

emerging neuromorphic model with great potential to dras-

tically promote the performance and eﬃciency of comput-

ing systems. However, an energy eﬃcient hardware imple-

mentation and the diﬃculty of training the model signiﬁ-

cantly limit the application of the spiking neural network.

In this work, we address these issues by building an SNN-

based energy eﬃcient system for real time classiﬁcation with

metal-oxide resistive switching random-access memory (R-

RAM) devices. We implement diﬀerent training algorithms

of SNN, including Spiking Time Dependent Plasticity (STD-

P) and Neural Sampling method. Our RRAM SNN systems

for these two training algorithms show good power eﬃciency

and recognition performance on realtime classiﬁcation tasks,

such as the MNIST digit recognition. Finally, we propose a

possible direction to further improve the classiﬁcation accu-

racy by boosting multiple SNNs.

1. INTRODUCTION

The era of Big Data brings new chances and new chal-

lenges in many ﬁelds especially for the applications need-

ing real-time data processing such as the EEG classiﬁcation,

tracking, etc[1, 2]. These applications demonstrate huge de-

mands for more powerful platforms with higher processing

speed, lower energy consumption, and more intelligent min-

ing algorithms. However, the classic “scaling down” method

is approaching the limit, making it more and more diﬃcult

for CMOS-based computing systems to achieve considerable

improvements from the device scaling [3]. Moreover, the

memory bandwidth required by high-performance CPUs has

also increased beyond what conventional memory architec-

tures can eﬃciently provide, leading to an ever-increasing

“memory wall” challenge to the eﬃciency of von Neumann

Permission to make digital or hard copies of all or part of this work for personal or

classroom use is granted without fee provided that copies are not made or distributed

for proﬁt or commercial advantage and that copies bear this notice and the full cita-

tion on the ﬁrst page. Copyrights for components of this work owned by others than

ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or re-

publish, to post on servers or to redistribute to lists, requires prior speciﬁc permission

and/or a fee. Request permissions from permissions@acm.org.

GLSVLSI’15, May 20–22, 2015, Pittsburgh, PA, USA.

 2015 ACM 978-1-4503-3474-7/15/05 ...$15.00.

http://dx.doi.org/10.1145/2742060.2743756 .

architecture. Therefore, innovation in both device technolo-

gy and computing architecture is required to overcome these

challenges.

The spiking neural network (SNN) is an emerging model

which encodes and processes information with sparse time-

encoded neural signals in parallel [4]. As a bio-inspired ar-

chitecture abstracted from actual neural system, SNN not

only provides a promising solution to deal with cognitive

tasks, such as the object detection and speech recognition,

but also inspires new computational paradigms beyond the

von Neumann architecture and boolean logics, which can

drastically promote the performance and eﬃciency of com-

puting systems [5, 6].

However, an energy eﬃcient hardware implementation and

the diﬃculty of training the model remain as two important

impediments that limit the application of the spiking neural

network.

On the one hand, we need an applicable computing plat-

form to utilize the potential ability of SNN. IBM proposes

a neurosynaptic core named TrueNorth [7]. To mimic the

ultra-low-power processing of brain, TrueNorth uses several

approaches to reduce the power consumption. Speciﬁcally,

TrueNorth uses digital messages between neurons to reduce

the communication overhead and event-driven strategy to

further save the energy computation [6]. However, the C-

MOS based implementation still has some limitations that

are hard to avoid, while some RRAM’s inherent advantages

can overcome these diﬃculties. First, on-chip SRAM, where

the synapse information is stored, is a kind of volatile mem-

ory with considerable leakage power, while RRAM is non-

volatile with very low leakage power [8]. Another limitation

is that TrueNorth may still needs adders to provide the addi-

tion operation of neuron function, but RRAM crossbar can

do the addition, or the matrix-vector multiplication, with

ultra-high energy eﬃciency by naturally combing the com-

putation and memory together [9, 10, 11]. Consequently,

RRAM shows potential on implementing low-power spiking

neural network.

On the other hand, from the perspective of algorithm, the

eﬃcient training of SNN and mapping a trained SNN onto

neuromorphic hardware presents unique challenges. Recen-

t work of SNN mainly focuses on increasing the scalability

and level of realism in neural simulation by modeling and

simulating thousands to billions of neurons in biological re-

al time [12, 13]. These techniques provide promising tools

to study the brain but few of them support practical cogni-

tive applications, such as the handwritten digit recognition.

Even TrueNorth [10] uses seven kinds of applications to ver-

下载后可阅读完整内容，剩余5页未读，立即下载

weixin_38656103

粉丝: 0
资源: 956

基于RRAM的低功耗神经突触网络：实时分类的突破

Circuit Design, Architecture and CAD for RRAM-based FPGAs

3d-rram 存储技术

2011 iedm 3d rram

rram 导论 缪向水 pdf

阻变存储器(rram)入门介绍

ncsu 45nm freepdk45 cmos

内存计算crossbar

为了提高DRAM的存储容量在工艺上可采取哪些措施?

国际半导体技术发展路线图_itrs(英文)-2015

存内计算芯片分为哪几类

最新资源

rram 导论缪向水 pdf