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

点击翻译按钮获取中文摘要

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.