같은 계산 그래프를 그려보면 비교적 쉽게 도출할 수 있을 겁니다. 자세한 설명은 프레드릭 크
레저트
Frederik
Kratzert
의 블로그
[
13
]
에서 찾을 수 있으니 궁금한 분은 참고하세요.
6.3.2
배치 정규화의 효과
그럼 배치 정규화 계층을 사용한 실험을 해봅시다. 우선은
MNIST
데이터셋을 사용하여 배치
정규화 계층을 사용할 때와 사용하지 않을 때의 학습 진도가 어떻게 달라지는지를 보겠습니다
(소스 코드는
ch06
/
batch
_
norm
_
test
.
py
에 있습니다). [그림
6
-
18
]이 그 결과입니다.
*
옮긴이_
γ
=
1
은
1
배 확대를 뜻하고
β
=
0
은 이동하지 않음을 뜻합니다. 즉, 처음에는 원본 그대로에서 시작한다는 이야기입니다. ...
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.
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.
Head of Cybersecurity
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.
Field Engineer
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.
Data Platform Tech Lead
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.