Avoiding Shortcut Solutions in Machine Learning Models
Listen now
Description
In this podcast Joshua Robinson discusses his work at MIT and his recent, lead author paper on how contrastive learning might lead to more reliable predictions in AI. Josh’s paper is at the NeurIPS proceedings website:
https://papers.nips.cc/paper/2021/hash/27934a1f19d678a1377c257b9a780e80-Abstract.html.
More Episodes
This interview is reproduced with the kind permission of Dr. Maxwell Cooper, host of the DaVinci Hour podcasts. Dr. Cooper interviews John Banja on various topics related to the ethical dimension of AI in radiology and on medical error in radiology. Please visit Dr. Cooper’s DaVinci Hour...
Published 10/31/22
Published 10/31/22
Dr. Yvonne Lui from NYU discusses her radiology research on brain injuries and on growing a clinical and research program in artificial intelligence.
Published 10/25/22
Links
Twitter
Facebook
Instagram
Patreon
Genres
Artwork or description wrong?
Request an update »
Updates may take a few minutes.
Do you host a podcast?
Track your ranks and reviews from Spotify, Apple Podcasts and more.
