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.

Neural Network Risks Suggested by Optical Illusions

Study: Deep neural networks don't see the world the way we do

Neural Networks Don't Understand What Optical Illusions Are

The Fascinating World of Optical Illusions: A Visual Deception

Eye Tricks: Why Our Eyes See Optical Illusions

Optical illusions and why neural networks can't seem to figure them out - Genetic Literacy Project

Algorithms, Free Full-Text

Now You See It, Now You Don't: Visual Illusions in Radiology

Low-Cost Optical Illusion Fluid Display Device

The Evolution of Electronic Dance Music 9781501366369, 9781501379598, 9781501366390, 9781501366383

Do Neural Networks Get Fooled by Visual Illusions?

A New Kind of Visual Illusion Uncovers How Our Brains Connect the

Low-Cost Optical Illusion Fluid Display Device