Search

Home > Data Skeptic > Black Boxes Are Not Required
Podcast: Data Skeptic
Episode:

Black Boxes Are Not Required
Category: Religion & Spirituality
Duration: 00:32:29
Publish Date: 2020-06-05 14:59:00
Description:

Deep neural networks are undeniably effective. They rely on such a high number of parameters, that htey are appropriately described as “black boxes”.

While black boxes lack desirably properties like interpretability and explainability, in some cases, their accuracy makes them incredibly useful.

But does achiving “usefulness” require a black box? Can we be sure an equally valid but simpler solution does not exist?

Cynthia Rudin helps us answer that question. We discuss her recent paper with co-author Joanna Radin titled (spoiler warning)…

Why Are We Using Black Box Models in AI When We Don’t Need To? A Lesson From An Explainable AI Competition
Total Play: 0

Users also like

300+ Episodes
Good Law | B .. 80+     10+
400+ Episodes
The Knowledg .. 200+     10+
1K+ Episodes
Entrepreneur .. 600+     50+