NEURAL MODEL OF ADAPTIVE HAND-EYE COORDINATION FOR SINGLE POSTURES
NEURAL MODEL OF ADAPTIVE HAND-EYE COORDINATION FOR SINGLE POSTURES
复制标题
DOI：
10.1126/science.3344437
复制
发表时间：
1988-03-11
期刊：
影响因子：
56.9
通讯作者：
KUPERSTEIN, M
中科院分区：
文献类型：
--
作者：
KUPERSTEIN, M
开发了一种神经网络模型，实现了多关节手臂的自适应视觉-运动协调，而不需要教师。该模型学习如何定位手臂，使其能够到达空间中任意位置的圆柱体。该模型使用了一种新的神经体系结构和一种修改神经连接强度的新算法。计算机仿真表明，该模型的平均位置误差为S臂长度的4%，平均姿态误差为4度。该模型可推广应用于任意数量的地形感觉输入与任意数量关节的肢体的协调。
A neural network model has been developed that achieves adaptive visual-motor coordination of a multijoint arm, without a teacher. The model learns to position an arm so that it reaches a cylinder arbitrarily positioned in space. The model uses a new neural architecture and a new algorithm for modifying neural-connection strengths. Computer simulations show that the model performs with an average position error of 4% of the arm''s length and with an average orientation error of 4.degree.. The model is designed to be generalized for coorinating any number of topographic sensory inputs with limbs of any number of joints.