Is the next plan to apply ml to ml for ml training 
If ML is applied to ML training, ML training should become faster and easier. Join us to help make it happen:https://twitter.com/woj_zaremba/status/1202300671212437504 …
-
-
-
Ah yes, like meta-meta learning https://www.bayeswatch.com/unofficial/meta-meta-learning.pdf … ;-)
Kraj razgovora
Novi razgovor -
-
Tweet je nedostupan.
-
-
Meta machine learning
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
What will OpenAI do differently? So far Google, BAIR, etc. have tried but failed to beat SGD and Adam.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
Might get Tensor Overflow
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
I tried messing with my compiler . And it kinda worked. An AI that chose syntax and codes for a given "objective" and used post training metrics as feedback for retraining. But im guessing open ai cant hire an iranian atm
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
I'm curious to know how much improvement over HyperBand or Population Based Training (PBT) you're seeking here. They have good implementations: https://ray.readthedocs.io/en/latest/tune.html … DeepMind also seems to like PBT a lot; they used it to help Waymo with their systems.
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.