Huh? What company did this? I’m skeptical
-
-
Replying to @vgr
Of course you are.. doesn't make it any less true. https://www.optimizingmind.com/ They're doing a funding round atm
1 reply 0 retweets 0 likes -
No joke
1 reply 0 retweets 0 likes -
There’s nothing on the site except a form. Are there published papers?
1 reply 0 retweets 0 likes -
Nope. It's not open as expected. It's someone's life work, and will be a service or licensed tech.
1 reply 0 retweets 0 likes -
ROFL... so a black box producing explanations for behaviors of other black boxes
Public-key decryptography1 reply 0 retweets 1 like -
Yes that's fair and it seems like it, but we can prove it easily. It can explain existing bb models and show that the explainable output is the only possible solution.
2 replies 0 retweets 1 like -
Hmm. By definition if you can produce a simple narrative about how an AI made a decision, to the degree of rigor you claim, then there’s no need for the AI as such. Might be a good thing, but count me skeptical.
1 reply 0 retweets 0 likes -
That is a very astute observation. The tech itself is an advanced algorithm that produces perfectly explainable models. On accident we disco'd that it can also perfectly explain any existing feed-forward models. One of the 1st needs was to "illuminate" existing bb models.
1 reply 0 retweets 0 likes
See Carlos’ post on ribbonfarm on the topichttps://www.ribbonfarm.com/2018/03/13/justifiable-ai/ …
-
-
Carlos knows his stuff, but there is a bit more depth to the problem and it's not pretty.
0 replies 0 retweets 0 likesThanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.