Easy take: calling linear algebra “quantum physics” and “artificial intelligence” is hype. Deeper: the huge influx of physicists into AI has produced an intellectual monoculture that isn’t capable of addressing key problems in the field.https://twitter.com/WIRED/status/1181437300414275584 …
-
-
Minimizing a cost function using SGD/backprop is like physics in much the same way as eigenvectors are part of quantum mechanics.
-
It occurs to me that I don't know where the theory of mathematical optimization (& notions like objective function, gradient descent) comes from. Certainly, it was buzzing as a subject independent of physics by the 1950s. But its roots may be in part in physics, earlier.
- 12 more replies
New conversation -
-
-
Hmm, I’m wondering if the disconnect here is that I learned backprop in ~1986, and maybe much more use of physical analogies was prevalent then?
-
Maybe. Hopfield networks were popular then, so I guess lots of interest in physics crossover at the time. But SGD is a notion from mathematical optimization. The closer you look at the energy surface idea, the less it has anything to do with gradient descent.
- 1 more reply
New conversation -
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.