CAREER: Facilitating Dependable Neuromorphic Computing: Vision, Architecture, and Impact on Programmability

职业：促进可靠的神经形态计算：愿景、架构和对可编程性的影响

• 批准号: 1942697
• 负责人: Anup Das
• 金额: $ 200万
• 依托单位: Drexel University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-03-01 至 2025-02-28
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1942697&HistoricalAwards=false
• 关键词: CAREER; Facilitating; Dependable; Neuromorphic; Computing

Machine learning is enabling rapid growth in new applications that rely on sustained and automated interpretation of data better than humans. Neuromorphic chips mimicking biological neurons and synapses execute machine learning algorithms in an energy-efficient manner. However, current neuromorphic architectures are inherently unreliable. They introduce errors during execution, limiting the dependability of machine learning. This project will address dependability challenges of neuromorphic computing, by looking at all levels, from building error-resilient machine learning algorithms to designing fault-tolerant hardware. This project will advance the field by 1) making neuromorphic computing reliable, efficient, programmable, and easy-to-use for the community, 2) teaching future science and engineering students how to make machine learning algorithms error-resilient, 3) creating job opportunities through national and international internships and collaborations, 4) raising interest of high school students in STEM through neuromorphic computing-enabled robotics workshops, and 5) building an integrated neuromorphic community through a new focused conference on neuromorphic computing. The research activities will be tightly integrated into teaching. Throughout this project, robot workshops will be organized annually for Drexel's Eureka (STEM for girls) and Philadelphia's high school students, jointly with the City of Philadelphia, to raise this community's interest in STEM. The project will also recruit undergraduate and graduate students in research and outreach activities, with emphasis on female and minority students.This project addresses broad research questions with far-reaching implications in dependable neuromorphic computing: What are the reliability issues in neuromorphic architectures and how to model them? How do these reliability issues manifest as errors and impact the performance of machine learning algorithms? How to improve error tolerance in these algorithms by exploiting error resilience and self-repair properties in the brain, and how to proactively mitigate reliability issues in neuromorphic architectures to avoid errors in the first place? This project seeks to answer these research questions through the following three key research activities: 1) embedding biological self-repair properties in machine learning algorithms; 2) designing fault-tolerant hardware to implement these algorithms; and 3) proactively mitigating reliability issues and facilitating fault tolerance in hardware through algorithm/architecture co-design and design/technology co-optimization.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

机器学习正在推动新应用程序的快速增长，这些应用程序比人类更好地依赖持续和自动的数据解释。模仿生物神经元和突触的神经形态芯片以节能的方式执行机器学习算法。然而，当前的神经形态架构本质上是不可靠的。它们在执行过程中引入错误，限制了机器学习的可靠性。该项目将通过从构建容错机器学习算法到设计容错硬件的各个层面来解决神经形态计算的可靠性挑战。该项目将通过以下方式推进该领域的发展：1) 使神经拟态计算变得可靠、高效、可编程且易于社区使用，2) 教授未来的科学和工程专业学生如何使机器学习算法具有容错性，3) 创造就业机会通过国内和国际实习和合作获得机会，4）通过支持神经拟态计算的机器人研讨会提高高中生对 STEM 的兴趣，5）通过新的神经拟态计算重点会议建立一个综合的神经拟态社区。研究活动将与教学紧密结合。在整个项目中，每年将与费城市联合为 Drexel 的尤里卡（女孩的 STEM）和费城的高中生举办机器人研讨会，以提高该社区对 STEM 的兴趣。该项目还将招募本科生和研究生参与研究和推广活动，重点是女性和少数族裔学生。该项目解决了对可靠的神经拟态计算具有深远影响的广泛研究问题：神经拟态架构中的可靠性问题是什么以及如何解决这些问题。为他们建模？这些可靠性问题如何表现为错误并影响机器学习算法的性能？如何通过利用大脑中的错误恢复和自我修复特性来提高这些算法的容错能力，以及如何主动缓解神经形态架构中的可靠性问题，从而从一开始就避免错误？该项目旨在通过以下三个关键研究活动来回答这些研究问题：1）将生物自我修复特性嵌入到机器学习算法中； 2）设计容错硬件来实现这些算法； 3) 通过算法/架构协同设计和设计/技术协同优化，主动缓解可靠性问题并促进硬件容错。该奖项反映了 NSF 的法定使命，并通过利用基金会的智力优势和更广泛的评估进行评估，认为值得支持。影响审查标准。

项目成果

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

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
• 发表时间: 2022
• 期刊: CF '22: Proceedings of the 19th ACM International Conference on Computing Frontiers
• 作者: Isik, Murat;Paul, Ankita;Varshika, M. Lakshmi;Das, Anup
• 通讯作者: Das, Anup

Improving Inference Lifetime of Neuromorphic Systems via Intelligent Synapse Mapping

通过智能突触映射提高神经形态系统的推理寿命

• DOI: 10.1109/asap52443.2021.00010
• 发表时间: 2021
• 期刊: Architectures and Processors (ASAP
• 作者: Song, Shihao;Titirsha, Twisha;Das, Anup
• 通讯作者: Das, Anup

Improving Dependability of Neuromorphic Computing With Non-Volatile Memory

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
• 作者: Song, Shihao;Das, Anup;Kandasamy, Nagarajan
• 通讯作者: Kandasamy, Nagarajan

Design of a Tunable Astrocyte Neuromorphic Circuitry with Adaptable Fault Tolerance

具有自适应容错能力的可调谐星形胶质细胞神经形态电路的设计

• DOI: 10.1109/mwscas57524.2023.10405978
• 发表时间: 2023
• 期刊: IEEE
• 作者: Varshika, M. L.;Johari, Sarah;Dubey, Jayanth;Das, Anup
• 通讯作者: Das, Anup

Aging-Aware Request Scheduling for Non-Volatile Main Memory

• DOI: 10.1145/3394885.3431529
• 发表时间: 2020-11
• 期刊: 2021 26th Asia and South Pacific Design Automation Conference (ASP-DAC)
• 作者: Shihao Song;Anup Das;O. Mutlu;Nagarajan Kandasamy