News for hackers. Stuff that matters.
Re:Our Machines Now Have Knowledge We’ll Never Understand by KirinDave on Monday May 01, 2017 @09:21PM (#14243271)
If we spent the same amount of effort working to visualize RNNs (and train them to explain themselves) as we did whining about how Turing machines are not very observable AGAIN, we'd have ML systems directly synthesizing the JARVIS voice to give us their reasons.

The fact that we can't observe specifically how a brain works doesn't mean we can't work out some structure. The fact an ant doesn't explain to us the individual rules to us doesn't mean we can't divine them via observation.

These articles irritate me, because they act like NNs are magic and they are anything but.

There are no comments on this comment yet.