提出了一种利用多层面神经网络进行激光水下目标检测的新方法．理论分析和实验表明，新方法不仅适用于不同的激光探测系统参数，而且适用于对不同海域情况下的自动目标弱信号的检测 A new method of laser underwater target detection using multilayer neural network is proposed. Theoretical analysis and experiments show that the new method is not only suitable for different laser detection system parameters, but also suitable for the detection of weak signals of automatic target in different sea areas