Reconfigurable all-optical nonlinear activation functions for neuromorphic photonics

We experimentally demonstrate all-optical reconfigurable nonlinear activation functions in a cavity-loaded Mach-Zehnder interferometer device on a silicon photonics platform, via the free-carrier dispersion effect. Our device is programmable to generate various nonlinear activation functions, including sigmoid, radial-basis, clamped rectified linear unit, and softplus, with tunable thresholds. We simulate benchmark tasks such as XOR and MNIST handwritten digit classifications with experimentally measured activation functions and obtain accuracies of 100% and 94%, respectively. Our device can serve as nonlinear units in photonic neural networks, while its nonlinear transfer function can be flexibly programmed to optimize the performance of different neuromorphic tasks.