Viewing profile — vark90
vark90
HN member- Joined
- Fri, Dec 23, 2016, 1:59 PM UTC
- HN karma
- 23
- Public activity
- 8 items
- HN profile
- View on Hacker News ↗
About vark90
No profile information was provided.
Recent public activity
-
comment
Comment #41950386
Hey! We have just published a review and benchmark of different uncertainty estimation techniques [1], it might be interesting to you if you want to get a general understanding of …
-
comment
Comment #41950262
You are right that uncertainty is a kinda loosely defined term. Usually people mean that it's a kind of proxy to the probability that the output of the model is correct in some sen…
-
comment
Comment #41950200
Yep, usually it's called abstention or rejection. When people in this field compare various methods of quantifying model uncertainty, they often perform what is called rejection ve…
-
comment
Comment #41950131
The idea behind semantic entropy (estimating entropy of distribution over semantic units, instead of individual sequences in the output space) is great, but it's somewhat naive in …
-
comment
Comment #18922684
Yep, he has an extremely charming personality judging from his videos. Something similar is about Robert Sapolski, also from Stanford. Love watching these guys lecture. Natural bor…
-
comment
Comment #18827622
A somewhat relevant question: what is a good way to get into longevity research/research support for a software engineer with a degree in optical engineering, who recently started …
-
comment
Comment #18824261
Man I wish I knew about this when I started my last pet project. Just finished the first major milestone, huge part of which was to create a basic bootstrap interface. This would'v…
-
comment
Comment #18680847
How useful do you think is studying general statistics from, for example, OpenStat vs. directly learning from ML-related courses like the one you mentioned?