categorical cross entropy

1 statements across 1 episodes · 0 bullish · 1 bearish · 1 people on the record · first statement Jun 20, 2023 by George Hotz · across every show →

Everything said about categorical cross entropy, oldest first

Jun 20, 2023 negative

Insight

Hotz: Training on internet cross-entropy loss yields mediocre AI responses

“The problem is, if your loss function is categorical across entropy on the internet, your responses will always be mid.”

George Hotz Jun 20, 2023 ▶ 57:15 Ep 18: Petaflops to the People — with George Hotz of tinycorp

Turn any episode into a week of clips.

This entire site, over 200 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.

categorical cross entropy

Everything said about categorical cross entropy, oldest first

Turn any episode into a week of clips.