i think the success of deep learning is less about neural networks specifically & more about gradient descent methods with a lot of data
@mat_kelcey At its core, it's about being liberated from the labor-intensive feature engineering that was the foundation of ML before.
-
-
@fchollet yeah I certainly feel sorry for a generation of CV researchers who focused on, say, SIFT features :(Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
@fchollet@mat_kelcey agree, GD on trillions of data points doesn't get you very far with poor features.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.