EFRI BRAID: Rapid contextual learning in resilient autonomous systems

EFRI BRAID：弹性自治系统中的快速情境学习

• 批准号: 2223811
• 负责人: Thomas Cleland
• 金额: $ 200万
• 依托单位: Cornell University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-10-01 至 2026-09-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2223811&HistoricalAwards=false
• 关键词: EFRI; BRAID; Rapid; contextual; learning

Neuromorphic computing seeks to identify key operational principles of the brain and implement them in artificial computing systems. The effort comprises both new hardware platforms with architectures based on decentralized brain networks (such as the Intel Loihi and IBM TrueNorth platforms) and the emerging computational algorithms that are required to run this new hardware effectively. In hardware, the diagnostic principles of this new computing paradigm are parallel, asynchronous local computation and the colocalization of memory and compute resources. This means that thousands of small processors all operate separately – without using a common clock, a shared memory store, or any other common resources that would slow the whole system down to the speed of its slowest component. The result is a computer system that can perform many types of tasks much faster, and with much lower energy expenditure, but that requires a complete rethinking of software algorithms in order to perform real-world tasks effectively using these fundamentally decentralized circuits. In the present application, computational principles extracted from biological brain circuits are employed to develop such working algorithms, and also to identify and analyze core computational motifs from these algorithms for future repurposing. Additional principles drawn from neuroscience also will be implemented and assessed, particularly local complexity and heterogeneity, in which the “neurons” can be individually complex and very different from one another, and adaptive network expansion, in which the network itself can grow in accordance with its acquired learning and expertise. Training and exposure to these transformative compute strategies will be broadened via multiple initiatives at Cornell and Georgia Tech, ranging from historically successful diversity, equity, and inclusion strategies to K-12 partnerships to immersive STEM teaching facilities and outreach programs. The potential advantages of neuromorphic computing platforms are both clear and profound, but also are limited by the paucity of well-developed neuromorphic algorithms capable of leveraging these advantages to address real-world problems. The Sapinet network, based on computational principles extracted from the biological olfactory system, shows promise as a neuromorphic algorithm for signal restoration and identification under noise. Using an explicit theoretical roadmap, this network architecture will be developed to incorporate additional brain-inspired strategies for resilient and robust autonomy, such as context dependence, multimodal integration, rich category learning, and explicit representations of similarity that together promise to enable superior and more sophisticated performance. Second, owing in part to the heterogeneity of design elements that underlie its power, neuromorphic computing presently is limited by a paucity of formal analysis and optimization techniques. A set of computational motifs (“numerical recipes”) and analysis strategies for neuromorphic operations will be developed, in service to future applications that may lack an explicit parallel in systems neuroscience. Finally, the resulting intelligent systems will be instantiated in software and in neuromorphic hardware, and ultimately in prototype devices for real-world deployment and testing. The overall goal is to construct and deploy locally intelligent, energy-efficient, and portable edge devices capable of a high degree of performance autonomy; i.e., that exhibit resilient and context-aware task performance under suboptimal and unpredictable real-world conditions.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.

神经形态计算旨在识别大脑的关键操作原则，并在人工计算系统中实现它们。 这项工作包括基于分散式大脑网络架构的新硬件平台（如英特尔Loihi和IBM TrueNorth平台）以及有效运行这种新硬件所需的新兴计算算法。 在硬件方面，这种新计算范例的诊断原则是并行、异步本地计算以及内存和计算资源的共定位。 这意味着成千上万的小型处理器都独立运行-而不使用公共时钟，共享内存存储或任何其他公共资源，这些资源会将整个系统的速度降低到其最慢组件的速度。 其结果是一个计算机系统，可以更快地执行许多类型的任务，并且能耗更低，但这需要对软件算法进行彻底的重新思考，以便使用这些基本分散的电路有效地执行现实世界的任务。在本申请中，采用从生物脑回路提取的计算原理来开发这样的工作算法，并且还识别和分析来自这些算法的核心计算基序以用于未来的再利用。 从神经科学中得出的其他原则也将被实施和评估，特别是局部复杂性和异质性，其中“神经元”可以是单独复杂的，彼此非常不同，以及自适应网络扩展，其中网络本身可以根据其获得的学习和专业知识增长。这些变革性计算战略的培训和接触将通过康奈尔大学和格鲁吉亚理工学院的多项举措来扩大，从历史上成功的多样性，公平性和包容性战略到K-12合作伙伴关系，再到沉浸式STEM教学设施和外展计划。 神经形态计算平台的潜在优势是明确而深刻的，但也受到缺乏能够利用这些优势来解决现实问题的开发良好的神经形态算法的限制。 Sapinet网络，基于从生物嗅觉系统中提取的计算原理，显示出作为噪声下信号恢复和识别的神经形态算法的希望。使用明确的理论路线图，该网络架构将被开发为包含额外的大脑启发策略，以实现弹性和强大的自主性，例如上下文依赖，多模式集成，丰富的类别学习和相似性的明确表示，这些策略共同承诺实现上级和更复杂的性能。 第二，部分由于异质性的设计元素，其权力的基础，神经形态计算目前是有限的形式分析和优化技术的缺乏。 一组计算图案（“数值食谱”）和神经形态操作的分析策略将被开发，在服务于未来的应用，可能缺乏一个明确的平行系统神经科学。 最后，最终的智能系统将在软件和神经形态硬件中实例化，并最终在原型设备中进行实际部署和测试。总体目标是构建和部署本地智能、节能和便携式边缘设备，这些设备能够实现高度的性能自主性;即，该奖项反映了NSF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。

项目成果

RealTHASC—a cyber-physical XR testbed for AI-supported real-time human autonomous systems collaborations

RealTHASC——一个网络物理 XR 测试平台，用于人工智能支持的实时人类自主系统协作

• DOI: 10.3389/frvir.2023.1210211
• 发表时间: 2023
• 期刊: Frontiers in Virtual Reality
• 作者: Paradise, Andre;Surve, Sushrut;Menezes, Jovan C.;Gupta, Madhav;Bisht, Vaibhav;Jang, Kyung Rak;Liu, Cong;Qiu, Suming;Dong, Junyi;Shin, Jane
• 通讯作者: Shin, Jane