AI can create images based on pictures you are looking at

Japanese scientists have create a creepy machine that can peer into your mind's eye with incredible accuracy.

The AI can study electrical signals in the brain to work out exactly what images someone is looking at, and even thinking about.

The technique could theoretically be used to create footage of daydreams and to help patients in permanent vegetative states to communicate with their loved ones. 

Scroll down for video

Scientists in Japan have developed an AI that can decode patterns in the brain to recreate what a person is seeing or imagining. This let them build up pictures of everything from simple shapes and letters to ducks and postboxes, seen or imagined by volunteers

Scientists in Japan have developed an AI that can decode patterns in the brain to recreate what a person is seeing or imagining. This let them build up pictures of everything from simple shapes and letters to ducks and postboxes, seen or imagined by volunteers

HOW IT WORKS 

The breakthrough relies on neural networks, which try to simulate the way the brain works in order to learn. 

These networks can be trained to recognise patterns in information - including speech, text data, or visual images - and are the basis for a large number of the developments in AI over recent years.

They use input from the digital world to learn, with practical applications like Google's language translation services, Facebook's facial recognition software and 's image altering live filters. 

The Kyoto team's deep neural network was trained using 50 natural images and the corresponding fMRI results from volunteers who were looking at them.

This recreated the images viewed by the volunteers.

They then used a second type of AI called a deep generative network to check that they looked like real images, refining them to make them more recognisable. 

The findings were made by researchers from the Kamitani Lab at Kyoto University, led by Professor Yukiyasu Kamitani.

Experts used a neural network to create images based on information taken from fMRI scans, which detect changes in blood flow to analyse electrical activity. 

Using this data, the machine was able to reconstruct owls, aircraft, stained-glass windows and red postboxes after three volunteers stared at the pictures. 

It also produced pictures of objects including squares, crosses, goldfish, swans, leopards and bowling balls that the participants imagined.

Although the accuracy varied from person to person, the breakthrough opens a 'unique window into our internal world', according to the Kyoto team.

Writing in a paper published in the online print repository BioRxiv, its authors said: 'Here, we present a novel image reconstruction method, in which the pixel values of an image are optimized to make its Deep Neural Network features similar to those decoded from human brain activity at multiple layers. 

'We found that the generated images resembled the stimulus images (both natural images and artificial shapes) and the subjective visual content during imagery. 

'While our model was solely trained with natural images, our method successfully generalized the reconstruction to artificial shapes, indicating that our model indeed 'reconstructs' or 'generates' images from brain activity, not simply matches to exemplars.'

The breakthrough relies on neural networks, which try to simulate the way the brain works in order to learn. 

Experts used a neural network to predict visual features based on information taken from fMRI scans, which detect changes in blood flow to analyse electrical activity. This let them build up pictures seen by or imagined by volunteers, like this iguana

Experts used a neural network to predict visual features based on information taken from fMRI scans, which detect changes in blood flow to analyse electrical activity. This let them build up pictures seen by or imagined by

read more from dailymail.....

Get the latest news delivered to your inbox

Follow us on social media networks

PREV Technology Ripple cryptocurrency hits a record high and is now up nearly 120 percent in a ...
NEXT Apple will replace ALL batteries for iPhone 6 or later