Artificial intelligence knows what you'll choose before you've made up your mind

Tuesday, 11 September 2018

AUT's Artificial Intelligence knows your choices before you do

Picture standing in your local dairy, indecisively scanning the drinks fridge to choose which can you're going to buy.

If you were hooked up to NeuCube, it would be able to predict which one you'd reach for – before you'd opened the fridge, and even before the thought was fully formed.

Using artificial intelligence to predict a person's choices before they have even made up their mind is a world first - and it was developed at Auckland University of Technology (AUT).

Professor Nikola Kasabov, who worked on the project, said they wanted to find out if there was brain activity before the conscious perception of an object.

* Don't fear the new AI revolution

* How computers 'see' faces and other objects

Our brains recognise branding before we even realise it - and it informs our decisions.

* How science may just end up killing crime**

There is, it turns out. Conscious perception happens 300 milliseconds after stimuli are presented, but peri-perception or preconscious perception occurs after 100 to 200 milliseconds.

That could bias the decision a person makes, Kasabov said.

'After conscious perception, the person is probably not making the decision, the decision was already made.'

In the project's experiment, 20 participants watched a video showing different drinks logos.

Their brain data was recorded using an EEG headset and synced to the NeuCube algorithm. NeuCube is a machine learning system modelled on how the human brain learns and recognises patterns.

The NeuCube could then predict what beverage the participants would choose 0.2 seconds before they consciously perceived the drink.

It showed a clear difference between logos which were familiar to participants and those that weren't. Our brains recognise branding before we even realise it.

It was also possible to detect which areas of the brain were triggered - whether the activity related to space, colour or time.

One of the other researchers, PhD student Zohreh Doborjeh, called that a 'game-changer' for marketing.

By marketing products in different ways and looking at the effect on brain data, brands would be able to see what appeals to consumers 'even at the preconscious level', Kasabov said.

The research has applications beyond marketing, however.

It could be revolutionary in police line-ups, allowing a victim who has blocked out a traumatic experience to pick out the offender.

It could also be used to detect criminal activity; if a suspect claimed not to recognise a crime scene or object, this could be tested on a preconscious level.

The first experiment may have focused on drink brands but the impact will be far wider than that, the team predicted.

AUT PhD students and sisters Zohreh and Maryam Doborjeh.

'The brain is an amazing thing - it learns and remembers things and can recognise them before the person can.

'To get a computer to be able to do that will change the way we all live,' said PhD student Maryam Doborjeh.

Those changes could start as early as next year, according to Kasabov. There has been strong interest in the practical applications of the research, and they expect to see something on the market by the beginning of 2019.

The research uncovers how we think, how much bias or prejudice we have - and how the choices we make often aren't conscious decisions at all, Kasabov said.

'This is an awakening signal that subconscious brain activities are strong. We cannot ignore them and sometimes they drive us, rather than we them.'