Avoiding Shortcut Solutions in Machine Learning Models

AI, Radiology and Ethics: A Podcast Series
14/03/2022 35 min

Listen "Avoiding Shortcut Solutions in Machine Learning Models"

Descargar episodio Ver en sitio original

Episode Synopsis

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 of the podcast AI, Radiology and Ethics: A Podcast Series

Discussing the Ethics of AI and Medical Error in Radiology 31/10/2022
Patients, Their Data, and Their Privacy 26/10/2022
The Complexity of Concussion and Growing a Program in AI 25/10/2022
The Business of AI in Radiology 20/09/2022
Health Disparities Revisited: Hopes and Challenges in Medicine and Radiology Practice 16/05/2022
On Reducing Error in Clinical Care with Artificial Intelligence 12/05/2022
AI in Health Disparities, Vendor-Hospital Agreements, and Refugee Resettlement 19/04/2022
PREVIEW of Episode 10: On Pigeons, Residency Training, and the Development of Expertise. 06/04/2022
On Pigeons, Residency Training, and the Development of Expertise. 15/11/2021
On AI and Health Disparities with Dr. Bibb Allen 08/11/2021
© 2003-2025 ZARZA | AHEAD OF OUR TIME
privacy policy
In God we trust In God we trust
PreSales Questions? Click Here
or call our toll-free line at +1-888-5002068 Miami, Florida, USA