Reconfigurable optical nonlinear activation functions using a phase-change microring for photonic neural networks
APL Photonics · 01.08.2026 · 11 (8)
DOI: 10.1063/5.0334562 ↗Kurz gefasst
Fachartikel in der Zeitschrift APL Photonics, online erschienen am 03.08.2026. Verfasst von Wentao Zhong und 5 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Natural Science Foundation of Guangdong, Shenzhen Science and Technology Innovation Commission.
Abstract (Originalsprache)
The implementation of reconfigurable nonlinear activation functions (NLAFs) is a key challenge in advancing photonic neural networks to model complex relationships. This study addresses this issue by introducing a device that exploits the phase-dependent optical properties of a Ge2Sb2Te5 superlattice (GST-SL) integrated on a silicon microring resonator. By manipulating the distinct absorption losses and refractive indices of the GST-SL across its crystallization states, we experimentally demonstrate five types of NLAFs: half-sigmoid, ELU, softplus, ReLU, and radial basis. The characterized functions exhibit a low activation power threshold of 1.76 mW and a high operational speed of up to 1 MHz. In a system-level benchmark using a three-convolutional-block neural network for MNIST handwritten digit classification, our activation functions boost the classification accuracy from 95.35% to 99.24%. These results highlight the promising performance and application potential of our device for future on-chip photonic neural networks and advanced optical computing.
Förderung
- National Natural Science Foundation of China
- National Natural Science Foundation of Guangdong
- Shenzhen Science and Technology Innovation Commission
- Scientific Instrument Developing Project of ShenZhen University
Zitieren
APA
Zhong, W., Dong, Y., Zhong, W., Wang, H., Shen, M., & Lei, L. (2026). Reconfigurable optical nonlinear activation functions using a phase-change microring for photonic neural networks. APL Photonics, 11(8). https://doi.org/10.1063/5.0334562
Vancouver
Zhong W, Dong Y, Zhong W, Wang H, Shen M, Lei L. Reconfigurable optical nonlinear activation functions using a phase-change microring for photonic neural networks. APL Photonics. 2026;11(8). doi:10.1063/5.0334562
BibTeX
@article{Zhong2026,
author = {Zhong, Wentao and Dong, Yida and Zhong, Wenlu and Wang, Haoqiang and Shen, Mei and Lei, Lei},
title = {Reconfigurable optical nonlinear activation functions using a phase-change microring for photonic neural networks},
journal = {APL Photonics},
year = {2026},
volume = {11},
number = {8},
doi = {10.1063/5.0334562}
}
EUVIMED