Re:Stop Explaining Black Box Models for High Stakes Decisions
by antpls on Saturday November 02, 2019 @04:53AM
(#21426601)
I didn't read the full paper yet, but a quick ctrl+f shows no mention of Activation Atlas for vision neural network, a collaboration between Google AI and OpenAI :
https://ai.googleblog.com/2019/03/exploring-neural-networks....
Also no mention of the "Unforeseen Attack Robustness" metric by OpenAI :
https://openai.com/blog/testing-robustness/
There are probably other publications for NLP models, all the big players are aware that explanation is key.