Generate Keras models from a description.https://twitter.com/mattshumer_/status/1287125015528341506 …
0:32
-
I have no doubt that building common models from a description can be automated, but I can't help but think it would be more effective to have a structured intermediate representation, and:
1. Use a supervised text model to go from description to structured representation, trained on a specialized dataset 2. Use a hard coded algorithm to generate Keras code from the structured representation (ensures code reliability)
-
-
Also, the right input for autoML is not a model description, but a task description and a dataset That said, this app demonstrates the power of GPT-3 for quick prototyping!
-
This could be one interesting direction for AutoML, getting from a non-expert user a description of the problem/dataset and some constraints, but rather than producing not model directly, output a description of the search space that then an AutoML strategy would optimize over.
- Show replies
New conversation -
-
-
Why go through another layer of structured representation?
-
Because you want to achieve generalization via interpolation, and forcing the interpolative model to deal with a huge layer of discrete complexity (code syntax) is a big hurdle for that. The simpler the structure of your target space the better. It's curve fitting after all
- 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.