On-chip spiking neural networks based on add-drop ring microresonators and electrically reconfigurable phase-change material photonic switches  

作　　者：QIANG ZHANG NING JIANG YIQUN ZHANG ANRAN LI HUANHUAN XIONG GANG HU YONGSHENG CAO KUN QIU 

机构地区：[1]School of Information and Communication Engineering,University of Electronic Science and Technology of China,Chengdu 611731,China

出　　处：《Photonics Research》2024年第4期755-766,共12页光子学研究（英文版）

基　　金：National Natural Science Foundation of China(62171087);Sichuan Science and Technology Program(2021JDJQ0023);Fundamental Research Funds for the Central Universities (ZYGX2019J003)。

摘　　要：We propose and numerically demonstrate a photonic computing primitive designed for integrated spiking neural networks (SNNs) based on add-drop ring microresonators (ADRMRs) and electrically reconfigurable phasechange material (PCM) photonic switches. In this neuromorphic system, the passive silicon-based ADRMR,equipped with a power-tunable auxiliary light, effectively demonstrates nonlinearity-induced dual neural dynamics encompassing spiking response and synaptic plasticity that can generate single-wavelength optical neural spikes with synaptic weight. By cascading these ADRMRs with different resonant wavelengths, weighted multiple-wavelength spikes can be feasibly output from the ADRMR-based hardware arrays when external wavelengthaddressable optical pulses are injected;subsequently, the cumulative power of these weighted output spikes is utilized to ascertain the activation status of the reconfigurable PCM photonic switches. Moreover, the reconfigurable mechanism driving the interconversion of the PCMs between the resonant-bonded crystalline states and the covalent-bonded amorphous states is achieved through precise thermal modulation. Drawing from the thermal properties, an innovative thermodynamic leaky integrate-and-firing (TLIF) neuron system is proposed. With the TLIF neuron system as the fundamental unit, a fully connected SNN is constructed to complete a classic deep learning task:the recognition of handwritten digit patterns. The simulation results reveal that the exemplary SNN can effectively recognize 10 numbers directly in the optical domain by employing the surrogate gradient algorithm. The theoretical verification of our architecture paves a whole new path for integrated photonic SNNs, with the potential to advance the field of neuromorphic photonic systems and enable more efficient spiking information processing.

关 键 词：neural networks PRECISE 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]