Roadmap on material-function mapping for photonic-electronic hybrid neural networks
Roadmap on material-function mapping for photonic-electronic hybrid neural networks
复制标题
DOI：
10.1063/1.5109689
复制
发表时间：
2019-10-01
期刊：
影响因子：
6.1
通讯作者：
Sorger, Volker J.
中科院分区：
文献类型：
--
作者：
Miscuglio, Mario;Adam, Gina C.;Sorger, Volker J.
人工神经网络中最先进的硬件仍然受到电子集成电路中已知的相同电容问题的影响。与其他新兴电子技术不同，光子学提供了适用于节点分布式非冯·诺依曼架构的低延迟互连性，依赖于密集的节点到节点通信。在此，我们通过详细研究单个节点感知器，为新兴的混合光子 - 电子神经网络提供了一个路线图。我们讨论了它如何在混合光子 - 电子异构技术中实现。此外，我们评估基于相变或强载流子色散效应的电光器件可以为训练后的神经网络中的感知器“权重”和非线性激活函数提供一条可行的途径，同时它也是接近代工厂工艺的材料。这项研究还评估了使用非线性光学材料作为高效且即时激活函数的优势。最后，我们确定了几个挑战，如果这些挑战得到解决，可能会加速将新兴存储材料的这种异构集成策略应用于近实时响应神经网络的集成光子学平台。（C）2019作者。
The state-of-the-art hardware in artificial neural networks is still affected by the same capacitive challenges known from electronic integrated circuits. Unlike other emerging electronic technologies, photonics provides low-delay interconnectivity suitable for node-distributed non-von Neumann architectures, relying on dense node-to-node communication. Here, we provide a roadmap to pave the way for emerging hybridized photonic-electronic neural networks by taking a detailed look into a single node perceptron. We discuss how it can be realized in hybrid photonic-electronic heterogeneous technologies. Furthermore, we assess that electro-optic devices based on phase change or strong carrier dispersive effects could provide a viable path for both the perceptron "weights" and the nonlinear activation function in trained neural networks, while simultaneously being foundry process-near materials. This study also assesses the advantages of using nonlinear optical materials as efficient and instantaneous activation functions. We finally identify several challenges that, if solved, could accelerate the adoption of such heterogeneous integration strategies of emerging memory materials into integrated photonics platforms for near real-time responsive neural networks. (C) 2019 Author(s).