CNN is able to learn without classification.
CNN is able to learn without classification.
Humans give names to sets of things.The habit of wanting to classify を持ってるのは、人間が例えば768次元のベクトルを覚えておいて他のベクトルと内積を計算する能力を持たない貧弱な計算能力の計算機だからだと思う/villagepump/nishio.icon Therefore, we try to compress the information by clustering it to only representative points, so that even a computer with poor computing power can manage. ---
This page is auto-translated from /nishio/CNNは分類せずに学習できている 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.