Towards Evaluating Computational Models of Intuitive Decision Making with fMRI Data

摘要: A vast array of everyday tasks require individuals to use intuition make decisions and act effectively, including civilian military professional such as those undertaken by firefighters, police, search rescue, small unit leaders, information analysts. To better understand train intuitive decision making (IDM), we envision future training systems will represent IDM through computational models these guide learning. This paper presents the first steps problem validating IDM. test if correlate with human performance, examine methods analyze functional magnetic resonance imaging (fMRI) data participants performing tasks. In particular, a new deep learning representation called sum-product networks perform model-based fMRI analysis. Sum-product have been shown be simpler, faster, more effective than previous approaches, them ideal candidates for this computationally demanding