Is accuracy lost when you reduce the level of abstraction?
Some people claim that "when you reduce the level of abstraction, you lose accuracy," but that's a low-resolution perception.
Abstract descriptions of real events have less information from actual real events.
Increasing abstraction decreases accuracy.
On the other hand, mathematical concepts are abstract in nature.
To illustrate with a concrete example, the "generality" that the original model had is lost. The characteristic that a model can explain the behavior of a wide range of objects.
That's because more information leads to more restrictions.
Some people confuse these two phenomena, even though they are two different things.
2019-05-15 First published.
---
This page is auto-translated from /nishio/抽象度を落とすと正確性が失われるのか using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I'm very happy to spread my thought to non-Japanese readers.