[개념정리] Embedding란?
Embedding means converting data to a feature representation where certain properties can be represented by notions of distance. 거리의 개념으로서 표현될 수 있는 특성을 지닌 feature representation 으로 데이터를 바꾸는 것. 거리개념은 metric learning에서 자주 보인다. Example, a model trained on speech signals for speaker identification, may allow you to convert a speech snippet to a vector of numbers, such that another snippet from the sa..
