AI, Radiology and Ethics: A Podcast Series podcast

Avoiding Shortcut Solutions in Machine Learning Models

0:00
35:43
Reculer de 15 secondes
Avancer de 15 secondes

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.

D'autres épisodes de "AI, Radiology and Ethics: A Podcast Series"