Classification of Metal Handwritten Digits Based on Microwave Diffractive Deep Neural Network

Recently, optical diffractive deep neural networks (D2NNs) have shown unprecedented superiority in terms of processing speed and power consumption. However, in the microwave band, complicated classification based on D2NN needs further investigation, which may accelerate the artificial intelligent tasks and simplify systems. Here, a three-layer D2NN is constructed for handwritten digit classification in the microwave frequency. The excited electromagnetic wave, which passes through the metal plane engraved with different digit patterns as the input, will focus on the target plane at designated focal points through the D2NN platform. A detector array is deployed to collect the target plane energy for direct digit classification. Each layer of the proposed D2NN is composed of 1024 phase modulating meta-units, and the phase distribution is generated through the stochastic gradient descent algorithm applied on the dataset. The network realizes an accuracy rate of 90% in numeric simulations, together with a 100% accuracy rate on the eighteen fabricated samples on the built-up platform. The average focal efficiency reaches 18.7% and 11.7% in the simulation and experiment, respectively. The system can be seen as an alternative method for seamless in situ monitoring of security checks and near-field sensing. A diffractive deep neural network (D2NN) architecture at the microwave frequency band is reported. The simulation and experiment are both conducted, proving the network's capability of high-accuracy classification with a compact structure. An analysis discussing the feasibility of D2NN at a lower band is also presented, as well as some potential future applications.image