Black Boxes Are Not Required
Data Skeptic5 Kesä 2020

Black Boxes Are Not Required

Deep neural networks are undeniably effective. They rely on such a high number of parameters, that they 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




Jaksot(589)

Suosittua kategoriassa Tiede

rss-mita-tulisi-tietaa
rss-poliisin-mieli
utelias-mieli
hippokrateen-vastaanotolla
tiedekulma-podcast
docemilia
rss-lihavuudesta-podcast
filocast-filosofian-perusteet
rss-duodecim-lehti
sotataidon-ytimessa
mielipaivakirja
radio-antro
rss-totta-vai-tuubaa
rss-astetta-parempi-elama-podcast
rss-tiedetta-vai-tarinaa
rss-ilmasto-kriisissa
rss-ihmisen-aani
rss-ylistys-elaimille
rss-luontopodi-samuel-glassar-tutkii-luonnon-ihmeita
rss-lapsuuden-rakentajat-podcast