ReLU

1 statements across 1 episodes · 1 bullish · 0 bearish · 1 people on the record · first statement May 17, 2017 by Wojciech Zaremba · across every show →

Everything said about ReLU, oldest first

May 17, 2017 positive
Assertion Supported
Zaremba: ReLU activation empirically works way better than sigmoid in neural networks
“It turns out that the one which is even simpler Empirically works way better, which is called ReLU, Rectify Linear Unit, and this one is ridiculously simple.”
Wojciech Zaremba May 17, 2017 ▶ 20:18 An AI Primer with Wojciech Zaremba · Y Combinator
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 300 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.