Making choices is the activity that we all do daily, either consciously or unconsciously. On average an adult makes 35,000 choices each day (most of them are unconscious choices).
But the point that I want to make here that, this simple process that we daily do, is not that simple as it seems.
Neurons signal travels in our body at 268 miles/hour and they are the one that pretty much helps us to make quick and accurate choices based on our emotions and past memory.
For decisions making our brain relies on two separate networks, the first one determines the overall value and another one guides how you ultimately behave against encounter situation.
But decision making doesn’t limit here, there are many other things that also work together to make it happen, but the problem is that Brain is such a highly complicated machine that we haven’t dig out all yet.
Researchers at the Auckland University of Technology has found some success in this area, The AUT researchers have developed the world’s first artificial intelligence model that can predict a person’s choices before they have even made up their mind.
This AI model works with a new type of neural network called spiking neural networks. The spiking neural networks are one of the most useful and effective neural networks for finding the pattern’s in a person’s choices.
This type of neural network is also very important as it fills the gap between neuroscience and machine learning, using biologically-realistic models of neurons to carry out the computation.
The researchers use this spiking neural network to build there own modified neural network called NeuCube. NeuCube architecture very similar to SNN and the major tasks it performs are mapping, learning, and understanding of spatiotemporal brain data.
In order to predict person choices before they make it, Zohreh and Maryam Doborjeh (sisters) carried out an experiment with 20 participants.
The participants were told to watch a video of different beverage logos. The sister recorded their brain data using an EEG headset. The recorded data then submitted to NeuCube algorithm.
NeuCube then starts classifying patterns from the participant’s brains.
The system’s algorithm starts learning from data. The algorithm was able to predict their beverage choice 0.2 seconds before they consciously perceived the beverage. It also showed a clear difference between logos which were familiar to participants and those which weren’t.
This groundbreaking work can have a number of uses, including neuromarketing, cognitive studies and crime solving. One potential application would be the ability to determine an offender in a police line-up if a victim has blocked out the traumatic experience.
The project is run by a team from AUT’s Knowledge Engineering and Discovery Research Institute (KEDRI), which includes AUT Ph.D. students and sisters Zohreh and Maryam Doborjeh, their supervisor Professor Nikola Kasabov and Professor Alex Sumich from Nottingham Trent University.
Maryam Doborjeh, who is a specializes in machine learning, says witnessing the NeuCube algorithm work was amazing.
“The brain is an amazing thing – it learns and remembers things and can recognize them before the person can. To get a computer to be able to do that will change the way we all live.”
Zohreh Doborjeh, who is in charge of Brain Data Laboratory (EEGLAB, AUT) and specializes in the psychology element of the work, is interested in what the subconscious brain can tell us about a person’s decision-making.
“We know that only 10 percent of people’s decisions are intentionally made, the other 90 percent are made subconsciously by the brain based on previous experiences, history, genetics, and other factors. This work will be a game-changer for marketing in particular.”
Kasabov, the designer of NeuCube, says the finding will lead on to more research.
“Researchers and social scientists will use this to understand better how much bias or prejudice we have due to our sub-conscience; what are our true preferences in life, how can we communicate better, and how can we learn better?”
More in AI :