News for hackers. Stuff that matters.
Re:Computers Can Be Understood by JoshTriplett on Monday April 13, 2020 @12:36PM (#22857330)
There are numerous research results about building understandable, analyzable neural network models.

Most models don't bother, because that isn't a necessary step to get reasonable answers. But it's possible.

Re:Computers Can Be Understood by criddell on Monday April 13, 2020 @01:45PM (#22858042)
When the model is applied to a regulated part of the market, it's becoming apparent that the institutions using the model have to be able to defend it.

David Heinemeier Hansson (DHH) posted an interesting thread to Twitter after he was granted a credit limit 20x higher than his wife and the credit card company's initial response was it's just the algorithm.

https://twitter.com/dhh/status/1192540900393705474

Re:Computers Can Be Understood by shrimp_emoji on Monday April 13, 2020 @01:07PM (#22857649)
Really? That's encouraging. I thought we're heading into some ironic dark enlightenment horseshoe of blackboxiness where the only artificial intelligence that works is as inscrutable as the natural intelligence it was meant to compete with.