[论文解读] 2021 Roadmap on Neuromorphic Computing and Engineering

Arnab Neelim Mazumder, Morteza Hosseini+2 more|arXiv (Cornell University)|May 12, 2021

Advanced Memory and Neural Computing参考文献 8被引用 45

一句话总结

这篇2022年路线图综合了神经形态计算在材料、器件、电路、算法、应用和伦理方面的现状，提出了一类受大脑启发的系统，与冯·诺依曼架构相比可显著降低功耗。它指出功耗可能降低1000倍，并将神经形态系统定位为边缘智能和可持续人工智能的关键。

ABSTRACT

Modern computation based on the von Neumann architecture is today a mature cutting-edge science. In this architecture, processing and memory units are implemented as separate blocks interchanging data intensively and continuously. This data transfer is responsible for a large part of the power consumption. The next generation computer technology is expected to solve problems at the exascale. Even though these future computers will be incredibly powerful, if they are based on von Neumann type architectures, they will consume between 20 and 30 megawatts of power and will not have intrinsic physically built-in capabilities to learn or deal with complex and unstructured data as our brain does. Neuromorphic computing systems are aimed at addressing these needs. The human brain performs about 10^15 calculations per second using 20W and a 1.2L volume. By taking inspiration from biology, new generation computers could have much lower power consumption than conventional processors, could exploit integrated non-volatile memory and logic, and could be explicitly designed to support dynamic learning in the context of complex and unstructured data. Among their potential future applications, business, health care, social security, disease and viruses spreading control might be the most impactful at societal level. This roadmap envisages the potential applications of neuromorphic materials in cutting edge technologies and focuses on the design and fabrication of artificial neural systems. The contents of this roadmap will highlight the interdisciplinary nature of this activity which takes inspiration from biology, physics, mathematics, computer science and engineering. This will provide a roadmap to explore and consolidate new technology behind both present and future applications in many technologically relevant areas.

研究动机与目标

• 为神经形态计算在关键技术与伦理领域提供当前状态的快照及未来展望。
• 解决冯·诺依曼架构的局限性，特别是由于数据移动导致的高功耗问题。
• 探讨神经形态系统如何实现面向边缘设备和复杂数据的能效高、实时处理。
• 审视神经形态人工智能的伦理影响，包括自主性、责任归属、可持续性及社会影响。
• 通过识别材料、器件和系统集成中的关键挑战与机遇，为研究人员和政策制定者提供指导。

提出的方法

• 汇集来自18个国家的75位领先研究人员的观点，形成跨学科、共识导向的路线图。
• 将分析结构化为六个核心领域：材料、器件、神经形态电路、算法、应用和伦理。
• 评估新兴材料（如可变相变、铁电和价态变化存储器）在非易失性、低功耗运行中的潜力。
• 评估器件层面的创新，包括电化学金属化单元和纳米线网络，用于突触模拟。
• 探索神经形态电路与算法的进展，包括脉冲神经网络和事件驱动处理。
• 整合伦理分析，重点关注可持续性、自主系统中的责任归属，以及长期社会影响。

实验结果

研究问题

• RQ1 神经形态系统如何克服传统冯·诺依曼计算架构的能效低下的问题？
• RQ2 哪些材料和器件最有望实现低功耗、可扩展的神经形态硬件？
• RQ3 在设计高效神经形态算法与系统级架构方面面临哪些关键挑战？
• RQ4 神经形态计算如何实现边缘设备和现实世界应用中的实际部署？
• RQ5 需要哪些伦理框架来指导神经形态人工智能系统的开发与部署？

主要发现

• 与最先进的机器学习方法相比，神经形态系统可将功耗降低多达三个数量级。
• 可变相变存储器、铁电器件和电化学金属化单元在突触模拟和非易失性运行方面展现出强大潜力。
• 事件驱动的脉冲神经网络架构可实现对动态、稀疏数据流的高效处理，且功耗极低。
• 神经形态技术有望通过将处理更靠近数据源，推动智能边缘计算的发展。
• 神经形态系统放大了人工智能自主性、责任归属和可持续性方面的伦理关切，但其能效优势也部分缓解了这些问题。
• 神经形态系统的发展可能加剧关于人工智能伦理的讨论，包括机器人权利和技术奇点等问题，尽管这些仍属推测性范畴。