I wish "Deep Learning" had been called "Compositional Function Approximation". It is a mouthful, but it would have avoided a very large amount of criticism that misses the point.
-
-
Maybe I am missing out on academic context. In the industries, it seems that DL is an almost universally accepted Holy Grail. It sometimes feels like people (like John in accounting) doubt your competence if you aren't building a deep learning model.
-
I am not so critical of deep learning per se (and fairly enthusiastic about the advances in computing related to it.) I feel like important discussions don't happen anymore: Biases, cost functions for the business, feature engineering, robustness, and limits of predictive power.
- 1 more reply
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.