NC unit secretary
2020-10-07 17:20:54

This is a discussion channel for “Interpretative Flexibility’ in AI and Neuroscience Research” by Dr. Arisa Ema (The University of Tokyo Institute for Future Initiatives). A link to the talk is the following. Please do not share the link to anyone outside of this slack workspace. Access Pass code can be found at the announcement channel.   URL: https://vimeo.com/471286637/d14f289d2e (14 minutes)

🙂 Toshio Tanaka, Loh Chen Lam, HiroHamada
👏 Taiki Miyagawa
Pat Chormai
2020-10-10 23:47:01

Dr. Ewa: thank you very much for this interesting talk! i’ve seen several neuroscience works use ML algorithms to predict activities or certain phenotypes from brain imaging data and often show or claim that signals from regions X, Y, Z can predict that outcome well. However, this data is typically needed heavy preprocessing steps before it can be used. So, I wonder whether how useful this kind of predictive approaches for neuroscience is in a long run (e.g. such results might just be due to spurious correlations from preprocessing steps). Would you mind sharing your comments on this?