视觉感知：立体视知觉的神经网络。
Visual Perception: Neural Networks for Stereopsis.
机构信息
Newcastle University, Institute of Neuroscience, Framlington Place, Newcastle upon Tyne, NE2 4HH, UK.
National Institutes of Health, National Eye Institute, Bldg 49 Room 2A50, Bethesda, Maryland 20892-4435, USA.
出版信息
Curr Biol. 2017 Jun 19;27(12):R594-R596. doi: 10.1016/j.cub.2017.05.013.
PMID:28633028
Abstract
How does our brain use differences between the images in our two eyes, binocular disparities, to generate depth perception? New work shows that a type of neural network trained on natural binocular images can learn parameters that match key properties of visual cortex. Most information is conveyed by cells which sense differences between the two eyes' images.
摘要
我们的大脑如何利用两个眼睛之间的图像差异（双眼视差）来产生深度感知？新的研究表明，在自然的双眼图像上训练的一种神经网络可以学习到与视觉皮层关键特性匹配的参数。大部分信息是由感知双眼图像差异的细胞传递的。
Zotero 插件