Conference: NSF International Workshop on Large Scale Neuromorphic Computing

该研讨会将与2022年国际神经形态系统会议（ICONS）一起举行。神经形态信息处理旨在发展人工神经系统，其设计原理基于生物神经系统。这种模式的优点包括低能耗容错计算和终身学习，使其成为下一代边缘人工智能系统的合理候选技术。目前的项目是一个为期半天的关于大规模神经形态计算基础设施的研究研讨会。本次研讨会将汇集全球公认的神经形态计算及其应用领域的领导者，以及国内公认的高性能计算领导者，就开发大规模神经形态计算系统并将其合并到异构网络基础设施中的机遇和挑战展开讨论。提议的研讨会旨在建立学术界、工业界、应用部门和国家研究实验室专家之间的持续对话，以确定方向并加速神经形态研究活动，以解决未来的网络基础设施需求。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The workshop will be held in conjunction with the International Conference on Neuromorphic Systems (ICONS) 2022. Neuromorphic information processing seeks to develop artificial neural systems, whose design principles are based on biological nervous systems. Advantages of this paradigm including low-energy fault-tolerant computing and life-long learning make this technology logical candidate for the next generation of AI systems at the edge.The present project is a half-day research workshop on large scale neuromorphic computing infrastructure. This workshop will bring together globally recognized leaders in neuromorphic computing and its application domains as well as nationally recognized HPC leaders to initiate discussions on the opportunities and challenges in developing large scale neuromorphic computing systems and merging them into heterogeneous cyberinfrastructure. The proposed workshop is intended to establish a continuous dialog between experts in academia, industry, application sectors, and national research labs, to shape the direction and accelerate neuromorphic research activities towards addressing the future cyberinfrastructure needs.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.