Generalization in vision and motor control
Generalization in vision and motor control
复制标题
DOI：
10.1038/nature03014
复制
发表时间：
2004-10-14
期刊：
影响因子：
64.8
通讯作者：
Bizzi, E
中科院分区：
文献类型：
--
作者：
Poggio, T;Bizzi, E
学习不仅仅是记忆。它不是简单地建立一个标记图像的查找表，或者一个类似电话目录的运动行为和相应的肌肉激活序列的列表。学习和智力的核心是预测能力，也就是说，超越对具体例子的记忆，对新情况进行概括。反过来，泛化的关键是系统的结构，而不是突触可塑性的规则。我们提出了一个具体的架构，为电机和视觉系统的泛化，并认为一个典型的微电路基础的视觉和电机学习。
Learning is more than memory. It is not simply the building of a look-up table of labelled images, or a phone-directory-like list of motor acts and the corresponding sequences of muscle activation. Central to learning and intelligence is the ability to predict, that is, to generalize to new situations, beyond the memory of specific examples. The key to generalization, in turn, is the architecture of the system, more than the rules of synaptic plasticity. We propose a specific architecture for generalization for both the motor and the visual systems, and argue for a canonical microcircuit underlying visual and motor learning.