CiNet Monthly Seminar

2021年9月22日（水）
15:00-17:00
On-lineで開催いたします

演題：Brain knows who is on the same wavelength

京都工芸繊維大学情報工学・人間科学系
助教
梶村 昇吾

担当 : 中野 珠実（北澤G）

Abstract:
Prediction of the initial compatibility of heterosexual individuals based on self-reported traits and preferences has not been successful, even with significantly developed information technology. I’ll talk about our recent attempt to overcome the limitations of self-reported measures and predict compatibility.
In this research, we used functional connectivity profiles from resting-state functional magnetic resonance imaging (fMRI) data.
Several days after collecting data from resting-state fMRIs, participants undertook a speed-dating experiment in which they had a 3-min speed date with every other opposite-sex participant.
Our machine learning algorithm successfully predicted whether pairs in the experiment were compatible or not using (dis)similarity of functional connectivity profiles obtained before the experiment.
The similarity and dissimilarity of functional connectivity between individuals and these multivariate relationships contributed to the prediction, hence suggesting the importance of complementarity (observed as dissimilarity) as well as the similarity between an individual and a potential partner during the initial attraction phase.
This research emphasizes the utility of neural information to predict complex phenomena in a social environment that behavioral measures alone cannot predict.