EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Reconfigurable Nonlinear Activation Using Low‐Loss Ge 3 Sb 2 Te 15 for Photonic Neural Networks

Yida Dong iD, Zhuoxuan Zhu iD, Yifan Zhu, Lichong Zhao, Lei Lei, Zihan Geng iD, Yida Li, X-D Xiang, Heshan Yu, Mei Shen iD

Nanophotonics · 27.07.2026 · 15 (14)

DOI: 10.1002/nap2.70212 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Nanophotonics, online erschienen am 14.07.2026. Verfasst von Yida Dong und 9 weiteren Autor:innen. Beteiligte Einrichtung: Southern University of Science and Technology Shenzhen China. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The escalating demand for high‐performance computing has spurred interest in integrated silicon photonics to overcome the constraints of traditional von Neumann architectures. Reconfigurable photonic devices with low optical loss, high‐speed switching, and nonvolatile operation are essential especially for photonic neural networks. This study introduces a robust high‐throughput methodology that serves as a primary engine for accelerating compositional search within the ternary Ge–Sb–Te (GST) system. Through this approach, we unveiled Ge 3 Sb 2 Te 15 (GST3215), a novel optical phase‐change material (OPCM) that mitigates the high optical losses inherent in conventional OPCMs like Ge 2 Sb 2 Te 5 (GST225). With reduced extinction coefficients and an improved figure of merit, GST3215 seamlessly integrates into hybrid silicon micro‐ring resonator (MRR), achieving lower insertion loss, a broader modulation range, and precise multilevel optical modulation—ideal traits for reconfigurable photonic systems. Moreover, GST3215 supports programmable nonlinear activation functions (e.g., ReLU, ELU, RBF) in a photonic neural network, lifting classification accuracy on the FashionMNIST dataset from 84.5% to 87.7%. These findings position GST3215 as a game‐changer for large‐scale photonic integration and optical computing.

Schlagwörter

Stichwörter der Autor:innen

Ge–Sb–Te systemintegrated silicon photonicsoptical phase‐change material (OPCM)reconfigurable non‐linear activation function

Autor:innen und Institutionen

  • Southern University of Science and Technology Shenzhen China.
  • Tianjin University Tianjin China.
  • Shenzhen Polytechnic University Shenzhen China.
  • Shenzhen University Shenzhen China.
  • Tsinghua Shenzhen International Graduate School Shenzhen China.

ORCID-Profile: Yida Dong, Zhuoxuan Zhu, Zihan Geng, Mei Shen

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Dong, Y., Zhu, Z., Zhu, Y., Zhao, L., Lei, L., Geng, Z., Li, Y., Xiang, X. D., Yu, H., & Shen, M. (2026). Reconfigurable Nonlinear Activation Using Low‐Loss Ge 3 Sb 2 Te 15 for Photonic Neural Networks. Nanophotonics, 15(14). https://doi.org/10.1002/nap2.70212

Vancouver

Dong Y, Zhu Z, Zhu Y, Zhao L, Lei L, Geng Z, et al. Reconfigurable Nonlinear Activation Using Low‐Loss Ge 3 Sb 2 Te 15 for Photonic Neural Networks. Nanophotonics. 2026;15(14). doi:10.1002/nap2.70212

BibTeX
@article{Dong2026,
  author = {Dong, Yida and Zhu, Zhuoxuan and Zhu, Yifan and Zhao, Lichong and Lei, Lei and Geng, Zihan and Li, Yida and Xiang, X-D and Yu, Heshan and Shen, Mei},
  title = {Reconfigurable Nonlinear Activation Using Low‐Loss Ge 3 Sb 2 Te 15 for Photonic Neural Networks},
  journal = {Nanophotonics},
  year = {2026},
  volume = {15},
  number = {14},
  doi = {10.1002/nap2.70212}
}
Kostenlos starten →