Low-threshold all-optical nonlinear activation function based on a Ge/Si hybrid structure in a microring resonator

Abstract

Optical nonlinear activation function is an indispensable part of the optical neural network. While linear matrix computation has thrived in an integrated optical neural network, there are many challenges for nonlinear activation function on a chip such as large latency, high power consumption and high threshold. Here, we demonstrate that Ge/Si hybrid structure would be a qualified candidate owing to its property of CMOS-compatibility, low nonlinear threshold and compact footprint. Thanks to the strong thermal-optic effect of germanium in conjunction with micro-ring resonator, we experimentally demonstrate three different types of nonlinear function (Radial basis, Relu and ELU functions) with a lowest threshold of 0.74 mW among our measured nonlinear functions and they can work well with a repetition rate below 100 kHz. Simultaneous size shrinkage of germanium and resonance constraint inside germanium is proposed to speed up response time. Furthermore, we apply our measured nonlinear activation function to the task of classification of MNIST handwritten digit image dataset and improve the test accuracy from 91.8% to 94.8% with feedforward full-connected neural network containing three hidden layers. It proves that our scheme has potential in the future optical neural network.

Neuromorphic Photonics Circuits: Contemporary Review

“…Since achieving nonlinearity of the characteristic only on photonic elements is a challenging task, many researchers are developing various combinations of photonic elements that can influence the characteristic for the necessary adjustment by electronic components. Also, solutions include using hybrid structures (Ge/Si hybrid structure in a micro-ring resonator) [76], structures using the free-carrier dispersion effect (scheme with a Mach-Zehnder interferometer loaded with MCR, heating elements, and a Mach-Zehnder coupler) [76][77][78] and another popular direction-phase change material (PCM) coatings [79,80]. The given examples can realize not one but several variants of activation functions: radial basis, sigmoid, softplus, Relu, and ELU.…”

On-chip electro-optical spiking VO₂/Si device with an inhibitory leaky integrate-and-fire response

“…Photonic activation functions can be built using all-optical or electro-optical devices. The all-optical approach benefits from a lower latency response than the optical-electrical-optical (O-E-O) conversion required by electro-optical devices [18][19][20][21]. However, current all-optical activation functions face an essential challenge since both the activation function's controlled (output) and controlling (input) optical signals affect its response.…”

Reconfigurable Low-Threshold All-Optical Nonlinear Activation Functions Based on an Add-Drop Silicon Microring Resonator

“…The NAF unit, which is responsible for nonlinearly mapping the input of the neuron to the output, is capable of enriching the application scenarios of the neural network [18,19]. In recent years, several photonic approaches have been proposed to realize NAFs [20][21][22][23][24][25][26][27][28][29][30][31][32]. For example, the optical-electricaloptical (O-E-O) method based on electro-absorption modulators [20,21] and photodetector-modulator structures [22][23][24] has been proposed to achieve electro-optical NAFs.…”

“…In 2020, an MZI-mesh structure is also proposed to implement different types of NAFs, which has a low threshold of 0.9 mW, but it needs five power supplies to precisely control the phase shift of each phase shifter, which increases the power consumption and the controlling complexity of the chip [31]. Reconfigurable all-optical NAFs, can also be achieved based on a germanium-silicon hybrid integrated MRR, which has a small footprint, but with an increased fabrication complexity [32], making it difficult for mass production. Therefore, an alloptical nonlinear activation unit with a low threshold, a small footprint, and a low fabrication complexity is highly desirable for large-scale integrated ONNs.…”