Neural networks don't understand what optical illusions are

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. But the visual system also has a well-known…
Machine-vision systems can match humans at recognizing faces and can even create realistic synthetic faces. But researchers have discovered that the same systems cannot recognize optical illusions, which means they also can’t create new ones.

Now you see it, now you don't: what optical illusions tell us

Optical Illusions Art Gallery - Little Passports, Optical Illusion

Convolutional neural networks can be tricked by the same visual

Optical Illusion Art: 5 Mind-Bending Works by Victor Vasarely

AI Can Spot Signs of Alzheimer's Before Your Family Does, by MIT Technology Review, MIT Technology Review

Algorithms, Free Full-Text

The Müller-Lyer Illusion Explained

Roman Yampolskiy - Associate Professor @ University of Louisville - Crunchbase Person Profile

Disappearing dots and seven other optical illusions freaking out

What are optical illusions and why do we like them so much?

Optical Illusions - Knowledia News

Teaching Computers to See Optical Illusions - Neuroscience News

Focus on the black dot in the center, hold and alienate your head