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 works and what doesn't in the specific…
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 sense. It's also true that uncertainty can…
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 verification. Basically, you continuously…
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 the sense that it considers these…
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 born teachers.
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 refreshing college math?
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've saved me a lot of time and effort,…
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?
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 works and what doesn't in the specific…
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 sense. It's also true that uncertainty can…
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 verification. Basically, you continuously…
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 the sense that it considers these…
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 born teachers.
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 refreshing college math?
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've saved me a lot of time and effort,…
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?