Tunable Nonlinear Activation Functions Enabled by WO₃ Films for Adaptive Diffractive Deep Neural Networks
Authors:
- 25 July 2025
- journal article
- Published by Wiley in Laser & Photonics Reviews
- Vol. 19 (24)
Abstract
Conventional electronics face intrinsic bandwidth and power constraints in deep learning, fueling the pursuit of optical computing's parallel processing and energy efficiency. A critical roadblock for optical neural networks (ONNs) lies in the missing trainable‐tunable nonlinear activation mechanisms required for modeling complex data correlations and cross‐task generalization. Here, this limitation is overcome through engineered tungsten trioxide (WO₃) thin films with dynamically controllable nonlinearity. Z‐scan measurements demonstrate stoichiometry‐dependent nonlinear responses modulated via photogenerated coloration, enabling precise control of optical nonlinearities. The films' non‐volatile memory effects permit implementation of adaptive in‐memory computing architectures where activation functions are trainable and task‐specifically optimized. This reconfigurable nonlinearity framework enhances both learning capability and generalization performance in ONNs, while achieving high‐performance THz‐scale response speeds (1 THz) for real‐time adaptive computing. Integrated as programmable activation layers in optical diffraction networks, the system demonstrates classification accuracy improvements of 4.62% (MNIST), 3.29% (Fashion‐MNIST), 13.53% (KMNIST), and 12.2% (CIFAR‐10). The synergistic combination of non‐volatile tunability, ultrafast reconfiguration, and stoichiometric control positions WO₃ thin films as a disruptive materials platform, resolving long‐standing activation function limitations in photonic neuromorphic systems while enabling adaptive high‐performance optical processors through on‐demand nonlinear engineering.Keywords
Funding Information
- Science and Technology Commission of Shanghai Municipality (21DZ1100500)
- National Natural Science Foundation of China (61975123)
- National Natural Science Foundation of China (62105206)
This publication has 50 references indexed in Scilit:
- MXene‐Nanoflakes‐Enabled All‐Optical Nonlinear Activation Function for On‐Chip Photonic Deep Neural NetworksAdvanced Materials, 2023
- Giant Nonlinear Optical Response of Graphene Oxide Thin Films Under the Photochemical and Photothermal ReductionAdvanced Materials Interfaces, 2022
- MXene‐Based Broadband Ultrafast Nonlinear Activator for Optical ComputingAdvanced Optical Materials, 2022
- Role of Oxygen Vacancy in the Photocarrier Dynamics of WO3 Photocatalysts: The Case of Recombination CentersThe Journal of Physical Chemistry C, 2022
- Broadband Nonlinear Photoresponse and Ultrafast Carrier Dynamics of 2D PdSe2Advanced Optical Materials, 2021
- Fast electrochemical activation of the broadband saturable absorption of tungsten oxide nanoporous filmNano Research, 2021
- Switching the Nonparametric Optical Nonlinearity of Tungsten Oxide by Electrical ModulationAdvanced Optical Materials, 2021
- Ultrafast Relaxation Dynamics and Nonlinear Response of Few‐Layer Niobium Carbide MXeneSmall Methods, 2020
- Charge Separation, Band-Bending, and Recombination in WO3 PhotoanodesThe Journal of Physical Chemistry Letters, 2019
- In situ Raman spectroscopy of the electrochemical reduction of WO3 thin films in various electrolytesSolar Energy Materials and Solar Cells, 2002