
Avoiding Shortcut Solutions in Machine Learning Models
0:00
35:43
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 from "AI, Radiology and Ethics: A Podcast Series"



Don't miss an episode of “AI, Radiology and Ethics: A Podcast Series” and subscribe to it in the GetPodcast app.








