权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

SNNnow: Probabilistic Learning for Deep Spiking Neural Networks: Foundations and Hardware Co-Optimization

SNNnow：深度尖峰神经网络的概率学习：基础和硬件协同优化

基本信息

批准号：
1710009
负责人：
Durgamadhab Misra
金额：
$ 38万
依托单位：
New Jersey Institute of Technology
依托单位国家：
美国
项目类别：
Standard Grant
财政年份：
2017
资助国家：
美国
起止时间：
2017-08-01 至 2022-07-31
项目状态：
已结题

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=1710009&HistoricalAwards=false
关键词：
SNNnow Probabilistic Learning Deep Spiking

项目摘要

Overview: Deep neural networks (DNN) have become the de-facto standard tool to carry out complex learningtasks. DNNs belong to the second generation of artificial neural networks (ANNs), which rely on neuronsthat implement memory-less non-linear transformations of the synaptic inputs. Motivated by the biologicalanalogy with the behavior of neurons in the brain, the third generation of neural networks, also referred toas Spiking Neural Networks (SNNs), was introduced in the nineties. In SNNs, synaptic input and neuronaloutput signals are spike trains. This proposal argues that the time for the use of SNNs as machine learningtools has come, and sets forth a systematic approach for the design and implementation of SNNs as learningand inference machines.Intellectual merit: SNNs have a number of unique advantages as compared to ANNs: (i) They are event-basedsystems with natural sparsity properties, which have the potential to make deep learning machines feasible forenergy-limited devices; (ii) They are uniquely capable to natively process data that comes in the form of timeencodedprocesses, for example, from bio-inspired sensors. The main goal of this project is the establishmentof a theoretical framework to enable the design of flexible spike-domain learning algorithms that are tailoredto the solution of supervised and unsupervised cognitive tasks, as well as their co-optimization on nanoscalehardware architectures. To this end, this project puts forth a principled probabilistic framework based on thegraphical formalism of Directed Information Graphs.Broader impact: The outcome of this research is expected to have a profound impact on the increasing numberof practical applications that are based on the processing of time-encoded signals, including biological sensorsand next-generation communication systems, and/or that require the adoption of computing solutions with asignificantly smaller power budget as compared to conventional DNNs. The research methodology is basedon a multi-disciplinary approach that integrates machine learning, information theory, probabilistic graphicalmodels, neuromorphic computing and device/system architecture at the nanoscale. The educational plan atthe home institution targets both undergraduate and graduate students via hands-on learning and experimentationactivities.

深度神经网络（DNN）已经成为执行复杂学习任务的事实上的标准工具。DNN属于第二代人工神经网络（ANN），它依赖于实现突触输入的无记忆非线性变换的神经元。受大脑中神经元行为的生物类比的启发，第三代神经网络，也被称为尖峰神经网络（SNN），在90年代被引入。在SNN中，突触输入和神经元输出信号是尖峰序列。该提案认为，使用SNN作为机器学习工具的时机已经到来，并提出了一个系统的方法，设计和实现SNN作为学习和推理机。智力优点：SNN有一些独特的优势相比，人工神经网络：（i）他们是基于事件的系统与自然稀疏属性，这有可能使深度学习机器可行的能量有限的设备;（ii）它们具有独特的能力，能够原生地处理以时间编码过程形式出现的数据，例如来自生物启发传感器的数据。该项目的主要目标是建立一个理论框架，以设计灵活的尖峰域学习算法，这些算法适合于有监督和无监督的认知任务的解决方案，以及它们在纳米级硬件架构上的协同优化。为此，该项目提出了一个基于有向信息图的图形形式主义的原则性概率框架。这项研究的成果预计将对越来越多的基于时间编码信号处理的实际应用产生深远的影响，包括生物传感器和下一代通信系统，和/或需要采用与传统DNN相比具有显著更小的功率预算的计算解决方案。该研究方法基于多学科方法，集成了机器学习，信息论，概率图形模型，神经形态计算和纳米级设备/系统架构。教育计划在家庭机构的目标是本科生和研究生通过动手学习和实验活动。

项目成果

期刊论文数量（14）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

An Introduction to Probabilistic Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications

DOI：
10.1109/msp.2019.2935234
发表时间：
2019-11-01
期刊：
IEEE SIGNAL PROCESSING MAGAZINE
影响因子：
14.9
作者：
Jang, Hyeryung;Simeone, Osvaldo;Gruening, Andre
通讯作者：
Gruening, Andre

Building Next-Generation AI systems: Co-Optimization of Algorithms, Architectures, and Nanoscale Memristive Devices

构建下一代人工智能系统：算法、架构和纳米级忆阻器件的协同优化

DOI：
10.1109/imw.2019.8739740
发表时间：
2019
期刊：
2019 IEEE 11th International Memory Workshop (IMW
影响因子：
0
作者：
Rajendran, Bipin;Sebastian, Abu;Eleftheriou, Evangelos
通讯作者：
Eleftheriou, Evangelos

FlexiDRAM: A Flexible in-DRAM Framework to Enable Parallel General-Purpose Computation

FlexiDRAM：一种灵活的 DRAM 框架，可实现并行通用计算

DOI：
10.1145/3531437.3539721
发表时间：
2022
期刊：
2022.
影响因子：
0
作者：
Zhou, R;Roohi, A;Misra, D;Angizi, S
通讯作者：
Angizi, S

Adversarial Training for Probabilistic Spiking Neural Networks

DOI：
10.1109/spawc.2018.8446003
发表时间：
2018-02
期刊：
2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC)
影响因子：
0
作者：
Alireza Bagheri;O. Simeone;B. Rajendran
通讯作者：
Alireza Bagheri;O. Simeone;B. Rajendran

Well-Posed Verilog-A Compact Model for Phase Change Memory

DOI：
10.1109/sispad.2018.8551667
发表时间：
2018-09
期刊：
2018 International Conference on Simulation of Semiconductor Processes and Devices (SISPAD)
影响因子：
0
作者：
Shruti R. Kulkarni;Deepak Kadetotad;Jae-sun Seo;B. Rajendran
通讯作者：
Shruti R. Kulkarni;Deepak Kadetotad;Jae-sun Seo;B. Rajendran