Federated Deep Learning Algorithm For Target Recognition Based On Trusted Network

Aiming at the high-precision target recognition algorithm that requires a large amount of data for training, but it is difficult to integrate small-scale fragmented data in different data islands and effectively apply the problem, a federated deep learning based on trusted network is proposed (Federated-Deep Learning, FDL) training framework, and use this framework to train image data distributed on different clients. Through the analysis of the experimental results of the federated deep learning framework, the practicability and feasibility of the framework are proved.