Lucas Beyer (Google DeepMind) - Convergence of Vision & Language

[@ajohny8954]

Your podcast has the potential to fill a very cool niche

[@mkamp]

Wow. What a great talk. Substantial, yet easy to follow. And that seems to be a characteristic of papers he co-authored as well. Great research, but also great education. 🎉

[@DeepFindr]

Nice talk and nice guy :)

[@HeHo-n6p]

Has someone more insight in what happens in the phase where the loss does not improve but it is still substantial to train on(i.e. have patience)? Seems to me there is still some significant weight reorganization taking place which not directly yields an improvement but sets the stage for the next lr phase

[@TheGenerationGapPodcast]

Lower local minimum terrain that was flat where the deritives are closer to zero for a long time

[@derekcarday]

the entire time I was worried if Lucas would get to where he needed to be on time

[@TheAIEpiphany]

Lol

[@gabehesch1]

Fabulous talk! Are these sides available to view or download?

[@TheGenerationGapPodcast]

Yes,it called screenshot

[@icriou]

would love to read the slide, plz?

[@quAdxify]

watch the video, literally :)

[@TheGenerationGapPodcast]

Screenshot