Massively scalable wavelength diverse integrated photonic linear neuron
Massively scalable wavelength diverse integrated photonic linear neuron
复制标题
大规模可扩展的波长多样化集成光子线性神经元
DOI：
10.1088/2634-4386/ac8ecc
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Preble, Stefan
中科院分区：
文献类型：
--
作者：
van Niekerk, Matthew;Rizzo, Anthony;Rubio, Hector;Leake, Gerald;Coleman, Daniel;Tison, Christopher;Fanto, Michael;Bergman, Keren;Preble, Stefan
随着大数据、云连接和物联网对计算资源的需求不断升级，开发新的低功耗、可扩展的架构势在必行。神经形态光子学或光子神经网络已经成为直接在芯片上物理实现高效算法的可行解决方案。这种应用主要是由于光的线性性质和硅光子学的可扩展性，特别是利用用于制造微电子芯片的大规模互补金属氧化物半导体制造基础设施。目前的神经形态光子实现源于两个范例：波长相干和非相干。在这里，我们介绍了一种新的架构，支持相干和非相干操作，以增加光子神经网络的能力和容量，与以前的演示相比，占用空间大大减少。作为一个原则的证明，我们实验证明了简单的加法和减法运算的晶圆制造的硅光子芯片。此外，我们通过实验验证了片上网络预测逻辑2位门AND，OR和XOR的准确度分别为96.8%，99%和98.5%。这种架构与高波长并行源兼容，从而实现大规模可扩展的光子神经网络。
As computing resource demands continue to escalate in the face of big data, cloud-connectivity and the internet of things, it has become imperative to develop new low-power, scalable architectures. Neuromorphic photonics, or photonic neural networks, have become a feasible solution for the physical implementation of efficient algorithms directly on-chip. This application is primarily due to the linear nature of light and the scalability of silicon photonics, specifically leveraging the wide-scale complementary metal-oxide-semiconductor manufacturing infrastructure used to fabricate microelectronics chips. Current neuromorphic photonic implementations stem from two paradigms: wavelength coherent and incoherent. Here, we introduce a novel architecture that supports coherent and incoherent operation to increase the capability and capacity of photonic neural networks with a dramatic reduction in footprint compared to previous demonstrations. As a proof-of-principle, we experimentally demonstrate simple addition and subtraction operations on a foundry-fabricated silicon photonic chip. Additionally, we experimentally validate an on-chip network to predict the logical 2 bit gates AND, OR, and XOR to accuracies of 96.8%, 99%, and 98.5%, respectively. This architecture is compatible with highly wavelength parallel sources, enabling massively scalable photonic neural networks.
用于超高效 SOI 热移相器的晶圆级兼容基板底切
DOI：
--
发表时间：
2022
期刊：
Conference on Lasers and Electro-Optics
影响因子：
--
作者：
Matthew van Niekerk;Venkatesh Deenadalayan;A. Rizzo;G. Leake;D. Coleman;C. Tison;M. Fanto;K. Bergman;S. Preble
通讯作者：
S. Preble
通过光子集成电路进行神经形态计算
DOI：
--
发表时间：
2020
期刊：
OPTO
影响因子：
--
作者：
G. Mourgias;A. Totović;N. Passalis;G. Dabos;A. Tefas;Nikos Pleros
通讯作者：
Nikos Pleros
具有 32GMAC/秒/轴突的硅集成相干神经元使用基于 EAM 的输入和加权单元计算线速率
DOI：
10.1109/ecoc52684.2021.9605987
发表时间：
2021
期刊：
2021 European Conference on Optical Communication (ECOC)
影响因子：
--
作者：
G. Giamougiannis;A. Tsakyridis;G. Mourgias;M. Moralis‐Pegios;A. Totović;G. Dabos;N. Passalis;M. Kirtas;N. Bamiedakis;A. Tefas;David Lazovsky;N. Pleros
通讯作者：
N. Pleros