You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
unlabeled data만 이용 - Can we learn a good feature representation that captures apparent similarity
among instances, instead of classes, ..? = unsupervised approach.
기존의 방법 능가 - our method surpasses the state of the-art on ImageNet classification by a large margin.
128차원으로..
구조
언급햇듯이, 클래스 단위가 아니라 instance 즉, image 한장을 마치 클래스 단위처럼..
softmax 계산량은?
실제 이런 문제는 word embeddings 힌트를 얻을 수 있음.
그래서, 이전 연구에서보면, 크게 hierarchical softmax, noise-contrastive estimation(NCE), negative sampling 등이 있는데 여기서는, NCE 방법 고려함. 참고로, tf에서 따로 구현되어 있음.
https://arxiv.org/abs/1805.01978
The text was updated successfully, but these errors were encountered: