이 합성곱 계층과 풀링 계층(정확히는 단순히 ‘원소를 줄이기’만 하는 서브샘플링 계층)을 반
복하고, 마지막으로 완전연결 계층을 거치면서 결과를 출력합니다.
그림
7-27ㅍ
LeNet
의 구성
[
20
]
LeNet
과 ‘현재의
CNN
’을 비교하면 몇 가지 면에서 차이가 있습니다. 첫 번째 차이는 활성화
함수입니다.
LeNet
은 시그모이드 함수를 사용하는 데 반해, 현재는 주로
ReLU
를 사용합니다.
또, 원래의
LeNet
은 서브샘플링을 하여 중간 데이터의 크기가 작아지지만 현재는 최대 풀링이
주류입니다.
이처럼
LeNet
과 현재의
CNN
은 얼마간 차이가 있지만 큰 차이는 아닙니다.
LeNet
이 지금부
터 거의
20
년 전에 제안된 ‘첫
CNN
’이라는 점을 생각하면 놀라운 일이죠.
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.