Abstract 이 연구에서는 large-scale image recongition setting에서 convolution network depth가 그 정확도에 미치는 영향을 조사한다. main contribution은 매우 작은 (3×3) convolution fi
Efficient Estimation of Word Representations in Vector Space
GloVe: Global Vectors for Word Representation
NEURAL MACHINE TRANSLATION BY JOINTLY LEARNING TO ALIGN AND TRANSLATE
Attention Is All You Need