立体神经视觉系统中零件识别的学习方法

提出了一种立体神经视觉系统中零件识别的学习方法。与标准的ＢＰ算法对比有两点改进：①用变尺度方向代替负梯度方向作为搜索方向；②用可变的最优学习率来代替不变的学习率，采用上述２仆改进后，训练速度和收敛性都有较大的改善，实际应用表明，所提出了垢训练速度、收敛性和稳定性都比标准ＢＰ算法有较大的提高。

Learning Mechanism for Parts Recognition in Stereoscopic Neuro-vision System

A learning mechanism for parts recognition(LMPR) in a stereoscopic nuro vision system is presented. It differs from the mechanism used in the standard back propagation (SBP) neural network in two ways. First, the searching direction is changed from the negative gradient direction to the variable metric direction. Secondly, the constant learning rate is changed to a variable optimal learning rate. With the combination of variable metric direction and variable optimal learning rate, the speed of the training process is greatly improved and the convergence is assured. Application examples are presented. The results have indicated that the proposed LMPR is superior in comparison with the SBP in the areas of learning speed, convergence and stability.