A Novel Hybrid Optical-Electronic Neural Network Approach to Task-Oriented Semantic Communications

Stacked intelligent metasurfaces (SIMs), composed of a multi-layered structure, have emerged as a powerful computing tool and analog signal processing platform for enabling task-oriented semantic communications (SemCom). However, SIMs lack nonlinear inference capabilities, thus motivating the emergence of the hybrid optical-electronic neural network (HOENN) that cascades a SIM and an electronic neural network (ENN). In this work, we investigate a disaster recognition taskoriented SemCom setting by leveraging the HOENN technology. Specifically, the HOENN is made of an optical neural network (ONN) using SIM mounted on an unmanned aerial vehicle (UAV) and a shallow ENN at the ground receiving station (GRS). The SIM automatically processes semantic information modulated on electromagnetic waves, with reduced energy consumption and ultrafast processing speed. At the GRS, the energy signals are processed by the shallow ENN to enhance the system's inference capability. The aim is to recognize the disaster according to the captured geomorphic images. To this end, we utilize a stochastic gradient descent algorithm to train the HOENN efficiently to minimize the cross-entropy between the recognized and actual semantics. Numerical results show that the HOENN surpasses the performance of using either ONN or ENN alone, achieving <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 7 \%}$</tex> recognition accuracy.