François Chollet @fchollet Deep learning @google. Creator of Keras, neural networks library. Author of 'Deep Learning with Python'. Opinions are my own. Jul. 03, 2019 1 min read

"why we are doing the research, why our tasks are particularly illustrative, why our methods are a step forward, whether performance is likely to increase or has reached a limit, is more important than performance measures because it tells us how research should proceed"

Paraphrased from Cohen and Howe 1988

Beating the state of the art is often a distraction from more important questions.

You can follow @fchollet.


Tip: mention @threader_app on a Twitter thread with the keyword “compile” to get a link to it.

Enjoy Threader? Sign up.

Threader is an independent project created by only two developers. The site gets 500,000+ visits a month and our iOS Twitter client was featured as an App of the Day by Apple. Running this space is expensive and time consuming. If you find Threader useful, please consider supporting us to make it a sustainable project.