[논문 리뷰] Attention is all you need - transformer란?

이번 글에서는 Attention is all you need 논문을 살펴봄과 동시에 논문에서 제시하는 아키텍처이자, 현재로서는 매우 중요해진 transformer에 대해 살펴보도록 하겠다. 논문 링크는 아래와 같다. Attention Is All You Need The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a..

원문링크 : [논문 리뷰] Attention is all you need - transformer란?