Advances in photonic neuromorphic computing (Conference Presentation)
Advances in photonic neuromorphic computing (Conference Presentation)
复制标题
光子神经形态计算的进展（会议演讲）
DOI：
10.1117/12.2509838
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
He, Sailing
中科院分区：
文献类型：
--
作者：
Sorger, Volker J.;George, Jonathan K.;Mehrabian, Armin;Shastri, Bhavin;El-Ghazawi, Tarek;Prucnal, Paul R.;Lee, El-Hang;He, Sailing
光子神经网络（PNN）是电子GPU执行机器学习任务的一种有前途的替代方案。PNN的价值主张源自i）向量矩阵乘法一旦训练就接近零的能耗，ii）10-100 ps短互连延迟，iii）经由fJ/比特高效的新兴电光器件提供的弱所需光学非线性。此外，光子集成电路（PIC）以低延迟提供高数据带宽，具有竞争力的占地面积和与微电子架构（如代工接入）的协同作用。这个演讲讨论了光子神经形态网络的最新进展，并提供了一个光子信息处理器的愿景。详细信息包括：1）计算性能技术在计算效率方面的比较（即MAC/J）和计算速度（即MAC/s），2）光子神经元的讨论，即感知器，3）架构网络实现，4）广播和加权协议，5）经由电光调制提供的非线性激活函数，（6）早期原型的实验演示。演讲将回答为什么神经网络是感兴趣的，并以PNN处理器的应用制度作为结论，这些处理器存在于深度学习，非线性优化和实时处理中。
Photonic neural networks (PNN) are a promising alternative to electronic GPUs to perform machine-learning tasks. The PNNs value proposition originates from i) near-zero energy consumption for vector matrix multiplication once trained, ii) 10-100 ps short interconnect delays, iii) weak required optical nonlinearity to be provided via fJ/bit efficient emerging electrooptic devices. Furthermore, photonic integrated circuits (PIC) offer high data bandwidth at low latency, with competitive footprints and synergies to microelectronics architectures such as foundry access. This talk discusses recent advances in photonic neuromorphic networks and provides a vision for photonic information processors. Details include, 1) a comparison of compute performance technologies with respect to compute efficiency (i.e. MAC/J) and compute speed (i.e. MAC/s), 2) a discussion of photonic neurons, i.e. perceptrons, 3) architectural network implementations, 4) a broadcast-and-weight protocol, 5) nonlinear activation functions provided via electro-optic modulation, and 6) experimental demonstrations of early-stage prototypes. The talk will open up answering why neural networks are of interest, and concludes with an application regime of PNN processors which reside in deep-learning, nonlinear optimization, and real-time processing.