In-Situ Training Optronic Convolutional Neural Network for SAR Target Recognition

For reducing computational burden of electronic hardware and increasing practical recognition performance of optron-ic convolutional network (OPCNN), here we propose an optical backpropagation algorithm and realize the in-situ training OPCNN in optical platform for SAR target recognition. Training networks according proposed algorithm, major computational operations in forward and backward propagating process are all executed in optics with the speed of light and low consumption. Several experiments on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset demonstrate the feasibility of proposed in-situ training algorithm.