A Simple Nonlinear Classifier Using a Multimode Optical Chip

Neural network accelerator based on photonic-integrated circuits is emerging as a promising technology for fast, power-efficient, and parallel computing. Under such technology, optics is mainly used for linear transformations, e.g., through an array of cascaded switching networks. Nonlinear activation is implemented either electronically requiring extra optical-electrical conversion or via nonlinear optical materials that often suffer from high loss, large power consumption, and difficulty in integration. Herein, an optical neural chip with only one multimode waveguide, fabricated using low-cost linear optical materials, plus seven heater electrodes to control the multimode interference, is proposed. The nonlinear networks are intrinsically integrated in the electrical-to-optical signal conversion through the waveguide. The linear computation, in the electronic domain, is included in the mandatory step to convert the input matrix to the intermediate current values on the seven electrodes. Though extremely simple, the proposed system can classify nonlinear datasets and images by optical readout with high accuracy and without calibration. Prospects for future development are given at the end. In this work, an alternative route is offered to exploiting the classic multimode interference for advanced optical computing applications. An optical neural chip is demonstrated with only one multimode waveguide and a few heater electrodes. The nonlinear activation is automatically integrated in the signal conversion process through a chain of electro-thermo-optical effects without extra optical-electrical conversion or nonlinear optical materials. Though extremely simple, the proposed system delivers high accuracy in classifying nonlinear datasets and images by optical readout.image (c) 2023 WILEY-VCH GmbH