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

机器学习正在推动新应用的快速增长，这些应用比人类更依赖于对数据的持续和自动化解释。模仿生物神经元和突触的神经形态芯片以一种节能的方式执行机器学习算法。然而，目前的神经形态结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。这个项目将解决神经形态计算的可靠性挑战，从构建容错机器学习算法到设计容错硬件，着眼于各个层面。该项目将通过以下方式推动该领域的发展：1)为社区提供可靠、高效、可编程和易于使用的神经形态计算；2)教授未来的理工科学生如何使机器学习算法具有容错能力；3)通过国内和国际实习和合作创造就业机会；4)通过支持神经形态计算的机器人研讨会提高高中生对STEM的兴趣；以及5)通过一个新的专注于神经形态计算的会议，建立一个综合的神经形态社区。研究活动将与教学紧密结合。在整个项目中，每年将与费城市政府联合为德雷克塞尔的Eureka(针对女孩的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。该项目还将在研究和推广活动中招收本科生和研究生，重点是女性和少数族裔学生。该项目解决了在可靠的神经形态计算中具有深远影响的广泛研究问题：神经形态体系结构中的可靠性问题是什么？如何对其进行建模？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性，以及如何主动缓解神经形态结构中的可靠性问题以避免错误？该项目试图通过以下三个关键研究活动来回答这些研究问题：1)在机器学习算法中嵌入生物自我修复特性；2)设计容错硬件来实现这些算法；3)通过算法/架构联合设计和设计/技术联合优化，主动缓解可靠性问题并促进硬件中的容错。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

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.