New preprint from the lab: "Individual differences among deep neural network models."
https://www.biorxiv.org/content/10.1101/2020.01.08.898288v1 …
Work with @KriegeskorteLab, @HannesMehrer, and Courtney Spoerer. #tweeprint below. 1/7
-
-
Dropout can help, but considerable differences remain. This calls into question the practice of using single network instances to derive neuroscientific insight. Going forward, multiple DNNs may need to be analysed (similar to experimental participants). /finpic.twitter.com/KJWbuPSGb9
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
One thing that several people talked about at the
@deepmath1 meeting is that it's probably misleading to think about the objective and the learning as separate - it's the trajectory that matters! -
Interesting, would love to learn more. We do look at training trajectories in the paper, too, to see when the representations are affected most and when they start to stagnate.pic.twitter.com/UdTV7RayFB
Kraj razgovora
Novi razgovor -
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.