论文部分内容阅读
在增量算法的基础上,利用截断(Clipping)方法和蒙塔卡罗(MonteCarlo)算法,对以四类飞行目标平面旋转投影作为学习样本的级联神经网络互连权重进行了二值优化处理,并用非学习样本进行了容错性检验,计算机模拟得到了满意的结果
Based on the incremental algorithm, the binomial optimization of cascaded neural network interconnection weights with plane rotation projection of four kinds of flight targets as learning samples is carried out by the method of Clipping and Monte Carlo. , And conducted a fault-tolerant test with non-learning samples. The computer simulation results were satisfactory