Researchers created a model of the brain using A.I.
We all like to think that we know ourselves best, but since our brain activity is largely governed by our subconscious mind, probably our brain knows us better. While this is only a hypothesis, researchers from Japan have already proposed a content recommendation system that assumes this to be true.
Essentially, when exposed to certain information, such a system uses the user’s brain signals (collected via an MRI scan), and over time, by examining numerous users and contents, it builds up a general model of brain activity. In this way, you can predict the user’s choices as if you had a copy of their brain’s behaviors.
“Once we obtain the ‘ultimate’ brain model, we should be able to perfectly estimate the brain activity of a person exposed to a specific content”, says Prof. Ryoichi Shinkuma from Shibaura Institute of Technology, Japan, who was a part of the team that came up with the idea. “This could provide powerful solutions in the commercial field, such as reducing the costs of targeted advertising”. In practice, by knowing the reactions of a given brain model it would be easier to better understand the biases of that brain.
However, a major drawback is the high cost of MRI. A typical brain scan would involve deployment and maintenance costs of an MRI, the labor costs of specialists, and the recruitment costs of a large number of participants. Faced with this challenge, Prof. Shinkuma and his team have come up with an ingenious solution: using profile information of people to infer their brain model.
In a new study published in the IEEE Transactions on Systems, Man, and Cybernetics: Systems, the team proposes a scheme for balancing the performance associated with inferring the brain model from profile information and the cost of acquiring that information.
“Our scheme utilizes machine learning (ML) to create a brain model based on inference of profile model”, explains Prof. Shinkuma. “To reduce the cost of information collection, we make use of the feature selection capability of ML to narrow down the number of questionnaire items by estimating the extent to which each item contributes to the inference performance”.
The questionnaire individual item contribution was quantified by assigning it an “importance score,” and only those with the highest were kept for inference. As a result, the team was able to maintain good inference performance while reducing the information cost.
To validate the effectiveness of their scheme, the team evaluated its performance accuracy using a brain model obtained experimentally and a profile model based on real profile information. They found that the scheme achieved nearly the same level of inference accuracy of the brain model as the case employing 209 questionnaires by using only 15-20 topmost items. This suggested that only the top 10% of questionnaire items were enough for inferring the brain model.
“An important next step will be to determine the best combination of ML and feature selection method for optimizing the performance of our scheme”, says Prof. Shinkuma. “At the same time, we will need to reduce the total computation cost for real-world applications involving a large number of users”.
Our knowledge of who we are may come from the outside in the not-too-distant future. Will A.I. be able to access our deepest privacy? Will brain models be sold to exploit other people’s reasonings? We should think about it.
Source neurosciencenews.com
