O'Reilly on Data

MARCH 26, 2024

There are lots of conversations about whether or not LLMs (and machine learning, more generally) are forms of compression or not. And, as it turns out, there happen to be certain prompts that act as keys that unlock training data (for insiders, you may recognize this as extraction attacks, a form of adversarial machine learning ).

Modeling 271

Modeling Machine Learning Risk Advertising 271

Domino Data Lab

JULY 1, 2021

statistical model-based techniques – Using Machine Learning we can streamline and simplify the process of building NER models, because this approach does not need a predefined exhaustive set of naming rules. The process of statistical learning can automatically extract said rules from a training dataset.

Modeling 111

Modeling Statistics Testing Metrics 111

The Unofficial Google Data Science Blog

JULY 18, 2023

Editor's note : The relationship between reliability and validity are somewhat analogous to that between the notions of statistical uncertainty and representational uncertainty introduced in an earlier post. While it may be a little abstract, this concept forms a key piece of Classical Test Theory (CTT) , a foundation of psychometrics.

Measurement 52

Measurement Metrics Uncertainty Slice and Dice 52