May 2020
Beginner to intermediate
952 pages
24h 11m
Korean
Content preview from 핸즈온 머신러닝(2판): 사이킷런, 케라스, 텐서플로 2를 활용한 머신러닝, 딥러닝 완벽 실무
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
660
2
부
신경망과 딥러닝
16.4.2
트랜스포머 구조: 어텐션이 필요한 전부다
2017
년 획기적인 한 논문
29
에서 구글 연구팀은 ‘어텐션이 필요한 전부다
Attention
is
all
you
need
’라고
제안했습니다. 연구자들은 트랜스포머
Transformer
라는 구조를 만들었습니다. 이 구조는 순환 층이
나 합성곱 층을 전혀 사용하지 않고
30
어텐션 메커니즘만(그리고 임베딩 층, 밀집 층, 정규화
층, 몇 가지 다른 구성 요소를 더해 ) 사용해
NMT
문제에서 최고 수준 성능을 크게 향상했습니
다. 추가적인 장점은 이 구조를 훨씬 빠르게 훈련할 수 있고 병렬화하기 쉽다는 것입니다. 따라
서 이전의 모델에서 최고 성능을 내기 위해 필요한 시간과 비용 일부만으로 훈련할 수 있습니
다. [그림
16
-
8
]에 트랜스포머 구조가 나타나 있습니다.
입력
출력
(오른쪽으로 이동)
위치 인코딩 위치 인코딩
멀티-헤드
어텐션
멀티-헤드
어텐션
마스크드
멀티-헤드
어텐션
입력 임베딩
출력 임베딩
덧셈 & 정규화
덧셈 & 정규화
덧셈 & 정규화
덧셈 & 정규화
선형
소프트맥스
출력 확률
덧셈 & 정규화
피드포워드
피드포워드
그림
16-8
트랜스포머 구조
31
29
Ashish
Vaswani
et
al
., “
Attention
Is
All
You
Need
,”
Proceedings
of
the
31st
International ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.