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
A good question to which I have no definite answer. We have compared differences that emerge from different random seeds (smallest intervention), differences due to different image sets (same categories), and differences due to different categories (Figure 5 in the paper).
-
-
I vaguely remember a pilot run in which we changed both, the weight seed and training order, but this did not result in stronger differences.
@HannesMehrer may remember better. -
Exactly as
@TimKietzmann said: pilot runs showed that when both the weight seed and training order were changed, this did not result in larger differences. Would be interesting to test this in more detail, e.g. varying only the training order.
Kraj razgovora
Novi razgovor -
-
-
oh yes, Figure 5 definitely insightful on the question (though slightly different). so different images in same categories and different random seeds operate roughly similarly on representational consistency. will take a deeper dive soon, thx.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
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.