-
## 一言でいうと
良質なデータを収集することで少量で高い転移学習性能を獲得する試み。事前学習済みモデルにプロンプトを与えデータの疑似ラベルを予測し、予測分布が一様で不確実性が高いデータを学習効果が高いとみなす。ベクトル空間上の距離をもとに周辺データも不確実性が高く、かつ採用するデータ間の距離が近すぎないよう調整し選択する。128 ラベルデータでフル学習の 90% 超の精度を達成。
#…
-
Hullo again, your friendly neighbourhood pedant here...
I've been having a look at the uncertainties package: https://pythonhosted.org/uncertainties/
which despite the info on that page is availab…
-
For the final step in propagating uncertainties from radiance units to brightness temperature units, applying the law of propagation of uncertainties yields very large uncertainties (hundreds of kelvi…
-
As described in this paper: https://www.sciencedirect.com/science/article/pii/S0039602816300632
A similar issue occurs for the posterior because the likelihood has a shape similar to SSR.
So we sh…
-
Improve and productize a `measurement` class and use it in the definition of the IAU system based on https://web.archive.org/web/20131110215339/http://asa.usno.navy.mil/static/files/2014/Astronomical_…
mpusz updated
8 months ago
-
Hi folks! And thank you for your project.
I want to use `pandera` to validate input dataframes of data transformation functions I have to write -- and I have a question.
**Is it possible to gene…
-
Implement it... using uncertainties package?
-
**Topic**
Uncertainty quantification: How is uncertainty measured, how do you validate it, how is it used?
**How is the topic relevant to the tric-dt themes?**
This topic came up in several conve…
-
## Abstract
In the rapidly evolving field of artificial intelligence (AI), aligning AI systems with human values and intentions, known as AI alignment, is of paramount importance. This whitepaper i…
-
It's time to take stock of where we are and dream about what's next. Here's a list of some things that might be next targets.
- Proper integration of KL eigenfunctions and boundary conditions (@br…