Neural networks don’t understand what optical illusions are

More from: | MIT |
0

Human vision is an extraordinary facility. Although it evolved in specific environments over many millions of years, it is capable of tasks that early visual systems never experienced. Reading is a good example, as is identifying artificial objects such as cars, planes, road signs, and so on.

Recommended for You

But the visual system also has a well-known set of shortcomings that we experience as optical illusions. Indeed, researchers have identified many ways in which these illusions cause humans to misjudge color, size, alignment, and movement.

The illusions themselves are interesting because they provide insight into the nature of the visual system and perception. So ways of finding

(...)

Read full article » https://www.technologyreview.com/s/612261/neural-networks-dont-understand-what-optical-illusions-are/


About | MIT |

MIT Technology Review is first to report on important new technologies that will affect your organization, your career, your life. Reporting on important technologies and innovators since 1899, with the backing of the world's #1 technology institute.

»Twitter: @techreview »Facebook: @technologyreview