When you purchase through links on our articles, Future and its syndication partners may earn a commission.

We love a good optical illusion here on Creative Bloq. Until now, we were also strangely happy to know that only humans (and cats) can see them while computers cannot. It seemed like a nice way to separate man from man and machine. A love of optical illusions was part of what made us human. Alas, artificial intelligence has come to change everything.

We’ve seen it before AI can create optical illusions. But now a researcher has created an AI system that can also perceive them, mimicking the way humans interpret complex optical illusions.

Computer vision is normally unable to simulate the psychological and neurological aspects of human vision, including our ability to recognize patterns. But a study published in APL machine learning by an AI researcher Ivan Maksymov from Charles Sturt University in Australia describes an AI that achieves this through “quantum tunneling”.

The system received the catchy nickname “quantum tunneling deep neural network”. As the name suggests, it combines quantum tunneling with a deep neural network, which is a series of machine learning algorithms inspired by the structure and function of the brain.

And the quantum tunnel? Here things get a little crazy. The phenomenon occurs when a subatomic particle such as an electron passes through an impenetrable barrier. It may seem impossible, but subatomic particles like light can behave like a wave. When not directly observed, they are not found in any fixed location, so there is a low probability that they are on the other side of the barrier. With enough subatomic particles present, some will “tunnel” through said barrier.

The AI ​​model was trained on two classic optical illusions: the Necker Cube and Rubin’s Vase. The model repeatedly saw the images, which were slightly altered each time they passed through the quantum tunneling stage. The deep neural network processed the variations and chose the perspectives they corresponded to, mimicking the way the human brain switches between perspectives when viewing an optical illusion.

“When we see an optical illusion with two possible interpretations (like the ambiguous cube or the vase and faces), researchers think we temporarily hold both interpretations at the same time, until our brain decides which image must be seen. This situation resembles the quantum illusion -mechanical thought experiment of Schrödinger’s cat”, writes Maksymov in a. publish on TechXplore.

Maksymov thinks the research could have practical benefits, possibly helping to educate airline pilots and astronauts about disorientation and misinterpretation of flight instruments. He believes the algorithm used could also help detect mild cognitive impairment and dementia.

In other AI news, a of autonomous AI art sold at Sotheby’s And The V&A in London organized an art screening on AI created from the brainwaves of human artists.