arXiv · 2311.01080
Optical ReLU-like Activation Function Based on a Semiconductor Laser with Optical Injection
Abstract
Artificial neural networks usually consist of successive linear multiply-accumulate operations and nonlinear activation functions. However, most optical neural networks only achieve the linear operation in the optical domain, while the optical implementation of activation function remains challenging. Here we present an optical ReLU-like activation function based on a semiconductor laser subject to the optical injection in experiment. The ReLU-like function is achieved in a broad regime above the Hopf bifurcation of the injection-locking diagram. In particular, the slope of the activation function is reconfigurable by tuning the frequency difference between the master laser and the slave laser.
Explore related subjects
Keep this discovery
Guanting Liu, Yiwei Shen, Ruiqian Li, Jingyi Yu, Xuming He, Cheng Wang. 2023-11-02. Optical ReLU-like Activation Function Based on a Semiconductor Laser with Optical Injection. https://arxiv.org/abs/2311.01080
Cite the original work for its findings. Save a collection to share your selection of sources.