[论文解读] A Survey of Neuromorphic Computing and Neural Networks in Hardware

Catherine D. Schuman, Thomas E. Potok+5 more|arXiv (Cornell University)|May 19, 2017

Advanced Memory and Neural Computing参考文献 1,597被引用 362

一句话总结

对神经形态计算和神经网络硬件的35年综合综述，详细介绍动机、模型、学习算法、硬件实现、支持系统和应用，并识别未来研究差距。

ABSTRACT

Neuromorphic computing has come to refer to a variety of brain-inspired computers, devices, and models that contrast the pervasive von Neumann computer architecture. This biologically inspired approach has created highly connected synthetic neurons and synapses that can be used to model neuroscience theories as well as solve challenging machine learning problems. The promise of the technology is to create a brain-like ability to learn and adapt, but the technical challenges are significant, starting with an accurate neuroscience model of how the brain works, to finding materials and engineering breakthroughs to build devices to support these models, to creating a programming framework so the systems can learn, to creating applications with brain-like capabilities. In this work, we provide a comprehensive survey of the research and motivations for neuromorphic computing over its history. We begin with a 35-year review of the motivations and drivers of neuromorphic computing, then look at the major research areas of the field, which we define as neuro-inspired models, algorithms and learning approaches, hardware and devices, supporting systems, and finally applications. We conclude with a broad discussion on the major research topics that need to be addressed in the coming years to see the promise of neuromorphic computing fulfilled. The goals of this work are to provide an exhaustive review of the research conducted in neuromorphic computing since the inception of the term, and to motivate further work by illuminating gaps in the field where new research is needed.

研究动机与目标

• 提供对神经形态计算领域的历史性和广泛概述。
• 总结推动神经形态硬件发展随时间演变的动机。
• 编目在硬件实现中使用的神经元、突触和网络模型。
• 评估适用于神经形态系统的学习算法和训练方法。
• 调查硬件实现、支持系统和应用，并确定未解决的研究问题。

提出的方法

• 对超过3,000篇论文、跨越35年的调研。
• 将工作分类为模型、算法/学习、硬件、支持系统和应用。
• 讨论具有硬件实现的主要神经元和突触模型。
• 分析诸如低功耗、实时性能和可扩展性等目标。
• 辨识差距与未来研究方向。

实验结果

研究问题

• RQ1 哪些历史动机塑造了神经形态计算，它们是如何演变的？
• RQ2 有哪些神经元、突触和网络模型具备硬件实现，它们有何区别？
• RQ3 神经形态硬件中普遍采用哪些学习规则和算法，它们是如何实现的？
• RQ4 使用了哪些硬件架构与材料，它们推动了哪些应用？
• RQ5 在推动神经形态计算方面，主要的开放挑战和差距是什么？

主要发现

• 在过去十年中，对神经形态计算的兴趣显著上升。
• 低功耗运行是现代神经形态硬件的主导动力。
• 存在各种神经元模型，涵盖生物可行、生物启发、积分-发放，以及McCulloch-Pitts传统。
• 突触模型通常强调可塑性和STDP，具有多样的突触动力学和网络学习规则。
• 硬件实现涵盖 spiking 和 non-spiking 网络，使用不同的器件技术和编程能力。
• 该领域仍然是跨学科的，涉及材料科学、神经科学、器件工程和算法/软件开发，并存在明确的开放研究差距。