I'd frame this as "DL seems generally capable at doing visual cortex-like stuff that traditional AI couldn't, AG being a special case of it"
The DL algorithms are little changed from mid-80s backprop which we ran on 1MHz processors. The main difference is GPU power. Brute force.
-
-
I guess main disagreement in this conversation is interest in theoretical novelty vs. practical relevance?
-
I don’t see that AlphaGo is practically relevant, nor that it provides meaningful evidence that DL will be practically relevant elsewhere.
- 7 more replies
New conversation -
-
-
Were that true there would be no difference in using different architectures. Everything would just be larger MLPs.
-
Yes, there has been an accumulation of “art, not science” knowledge of how to tweak architectures and hyperparameters.
- 3 more 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.