Convnets are a representationally-efficient way to do pattern recognition on data with continuous axes (time, space). No magic whatsoever. https://twitter.com/davidsuculum/status/854824527896993792 …
This Tweet is unavailable.
-
"representationally efficient" meaning here that it introduces modularity and hierarchy in the representations.
-
-
It's intuitive, but can it be/is it proved somehow (other than beating benchmarks)? Interested in any work on this.
-
I think It's already proved: Universal Approximation Theorem. Or if that is not what you mean, then what is?
- Show replies
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.