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 …
-
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.
-
-
There are some papers from mit and but arguing about how deep learning is made possible by the renormalization group
Thanks. 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.