Suppr超能文献

集成于通用磷化铟光子电路技术中的全光尖峰激光神经元。

All-optical spiking laser neuron integrated in generic InP photonic circuit technology.

作者信息

Puts Lukas, Lenstra Daan, Williams Kevin A, Yao Weiming

出版信息

Opt Express. 2025 Jun 30;33(13):27400-27413. doi: 10.1364/OE.560596.

Abstract

Brain-inspired, neuromorphic devices implemented in integrated photonic hardware have attracted significant interest as part of efforts towards non-von Neumann computing paradigms that use the low-loss, high-speed, and parallel operations in optics. We present here the design and measurements of an all-optical spiking laser neuron that was realized for the first time on a generic InP photonic foundry platform, which may be a practical alternative to other semi-integrated photonic and electronic-based spiking neuron implementations. The measured device demonstrates excitability, nanosecond refractory period, and self-pulsating capabilities. We show that the device offers sufficient optical gain for incoming spikes, an essential feature for directly cascading neurons. In addition, we demonstrate multi-wavelength injection and excitability and discuss the possibilities of combining this device with other on-chip photonic devices. The reported characteristics are an improvement over the state-of-the-art, because the proposed device allows for direct on-chip cascading of neurons and weights, which is essential for future fully connected, multi-wavelength, all-optical photonic spiking neural networks.

摘要

集成光子硬件中实现的受脑启发的神经形态器件,作为非冯·诺依曼计算范式努力的一部分,因其利用光学中的低损耗、高速和并行操作而备受关注。我们在此展示了一种全光脉冲激光神经元的设计与测量,该神经元首次在通用的磷化铟光子代工平台上实现,这可能是其他基于半集成光子和电子的脉冲神经元实现方式的一种实用替代方案。所测量的器件展示出兴奋性、纳秒级不应期和自脉冲能力。我们表明该器件为输入脉冲提供了足够的光学增益,这是直接级联神经元的一个基本特征。此外,我们展示了多波长注入和兴奋性,并讨论了将该器件与其他片上光子器件相结合的可能性。所报道的特性是对现有技术的改进,因为所提出的器件允许神经元和权重在芯片上直接级联,这对于未来完全连接的、多波长的、全光光子脉冲神经网络至关重要。

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验