The future of high-level APIs for AI is... a problem-specification API. Currently we only search over network weights, thus "problem specification" involves specifying a model architecture. In the future, it will just be: "tell me what data you have & what you are optimizing"
-
-
Thirty five years ago, I spent the summer building an expert system in Prolog to recommend various statistical tests for data!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Spot on.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
linear programming with modeling languages like GAMS is a lot like that. Describing the structure of the problem and therefore *what* should be solved instead of *how* to solve it.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Use regular PowerPoint files as the input, learn to create MVPs directly from slides with the proper boxology applied.https://twitter.com/fchollet/status/1082359528056733696?s=19 …
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.

