Re:Differential Equations with Transformers: Deep Learning f...
by throwlaplace on Wednesday March 11, 2020 @10:50AM
(#22546278)
I was a critic when this was first posted (and was promptly downvoted). I don't understand why this is getting traction (or even a research direction they decided to pursue). does anyone really believe this thing is doing some kind of symbolic reasoning? it's doing nothing but memorizing training examples! that it has nonzero performance in test is owing to the wonky metric.
[ Parent
| on HN ]
Re:Differential Equations with Transformers: Deep Learning f...
by jfkebwjsbx on Wednesday March 11, 2020 @11:37AM
(#22546681)
I am not one that hypes AI and ML, but I don't see the problem with this.
If this new system can integrate some equations that other methods cannot, I welcome it. It is almost instantaneous to check the solutions, so what is the problem?
I imagine the devs at Wolfram Mathematica are already working into adding this new kind of solvers into their overall integrator.
Re:Differential Equations with Transformers: Deep Learning f...
by whatshisface on Wednesday March 11, 2020 @11:09AM
(#22546438)
On one hand you have 1980s symbolic AI that can produce true, coherent statements, and on the other you have GPT-2 which can produce really nifty gibberish. If you could put the two together maybe that would be some progress. I can see that getting transformers to emulate symbolic math might be a step in that direction.
Re:Differential Equations with Transformers: Deep Learning f...
by throwlaplace on Wednesday March 11, 2020 @11:11AM
(#22546458)
that's not reasoning though. it's not even an expert system or prolog (because adversarial examples exist). it's very close to a million monkeys typing.