Ballard D H, Hinton G E, Sejnowski T J
Nature. 1983;306(5938):21-6. doi: 10.1038/306021a0.
The functional abilities and parallel architecture of the human visual system are a rich source of ideas about visual processing. Any visual task that we can perform quickly and effortlessly is likely to have a computational solution using a parallel algorithm. Recently, several such parallel algorithms have been found that exploit information implicit in an image to compute intrinsic properties of surfaces, such as surface orientation, reflectance and depth. These algorithms require a computational architecture that has similarities to that of visual cortex in primates.
人类视觉系统的功能能力和并行架构是有关视觉处理的丰富思想来源。我们能够快速且轻松执行的任何视觉任务，很可能都有一个使用并行算法的计算解决方案。最近，已经发现了几种这样的并行算法，它们利用图像中隐含的信息来计算表面的固有属性，例如表面方向、反射率和深度。这些算法需要一种与灵长类动物视觉皮层的计算架构相似的计算架构。
