High-level APIs, I should add. In the future, doing tensor-level manipulations will feel like writing assembly.
Show this thread
I suspect that less than 10 years from now, all of the DL training/architecture tricks that came from the arXiv firehose over 2015-2019 will have been entirely superseded by automated search techniques. The future: no alchemy, just clean APIs, and quite a bit of compute.
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
There is an urgent need for model management tools, that can store, query, and compare models and experiments. I believe that a GitHub-like repo for pretrained models can greatly advance Automatic Architecture Search.
-
You mean TF Hub?
End of conversation
New conversation -
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
We will put all the magic into automated search techinques. I can image that in the near future there will be neural automated search, which was trained on results of all arXiv papers.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Searching the right architecture for a problem is nice, but a neural model that auto-grow its own architecture as part of the learning process is the future as I see it.
-
That’s actually exactly what I’m working on!
- Show replies
New conversation -
-
-
Thanks! Our Auto-Keras project is still in a primitive stage. We are heading the same direction.
End of conversation
New conversation -
-
Until then, expertise mining arxiv is a competitive advantage.
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.