Programmable chalcogenide-based all-optical deep neural networks

We demonstrate a passive all-chalcogenide all-optical perceptron scheme. The network's nonlinear activation function (NLAF) relies on the nonlinear response of Ge2Sb2Te5 to femtosecond laser pulses. We measured the sub-picosecond time-resolved optical constants of Ge2Sb2Te5 at a wavelength of 1500 nm and used them to design a high-speed Ge2Sb2Te5-tuned microring resonator all-optical NLAF. The NLAF had a sigmoidal response when subjected to different laser fluence excitation and had a dynamic range of -9.7 dB. The perceptron's waveguide material was AlN because it allowed efficient heat dissipation during laser switching. A two-temperature analysis revealed that the operating speed of the NLAF is <= 1 ns. The percepton's nonvolatile weights were set using low-loss Sb2S3-tuned Mach Zehnder interferometers (MZIs). A three-layer deep neural network model was used to test the feasibility of the network scheme and a maximum training accuracy of 94.5% was obtained. Weconclude that combining Sb2S3-programmed MZI weights with the nonlinear response of Ge2Sb2Te5 to femtosecond pulses is sufficient to perform energy-efficient all-optical neural classifications at rates greater than 1 GHz.

Automated summary

The study demonstrated a passive all-chalcogenide all-optical perceptron scheme utilizing the nonlinear response of Ge2Sb2Te5 to femtosecond laser pulses. By testing different laser excitations, the designed NLAF showed a sigmoidal response with a dynamic range of -9.7 dB. The perceptron efficiently dissipated heat using AlN material and set nonvolatile weights through Sb2S3-tuned MZIs, achieving energy-efficient all-optical neural classifications at rates greater than 1 GHz.