立体神经视觉系统中零件识别的学习方法  

Learning Mechanism for Parts Recognition in Stereoscopic Neuro-vision System

作　　者：熊银根[1] 

机构地区：[1]中山大学无线电电子学系,广东广州510275

出　　处：《中山大学学报（自然科学版）》2000年第3期25-29,共5页Acta Scientiarum Naturalium Universitatis Sunyatseni

基　　金：广东省博士后基金资助项目

摘　　要：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个改进后 ,训练速度和收敛性都有较大的改善 .实际应用表明 ,所提出的学习方法的训练速度。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.

关 键 词：立体神经视觉 学习方法 神经网络 零件识别 装配 

分 类 号：TG95[金属学及工艺—钳工工艺] TP18[自动化与计算机技术—控制理论与控制工程]