December 2020
Beginner to intermediate
256 pages
5h 15m
Korean
Content preview from 안전한 인공지능 시스템을 위한 심층 신경망 강화
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.
51
3
장
심층 신경망
3.3
수학 함수로서의 심층 신경망 모델
지금까지는 뉴런과 그 상호 연결을 고려해 순수하게 개념적, 시각적으로 생물학적 뇌의 처리
과정과 유사한 심층 신경망을 생각했습니다. 그러나 심층 신경망을 포함한 머신러닝 모델은 실
제로 수학 함수입니다. 수학에서 함수는 복잡할 수 있지만 머신러닝 모델에서 함수는 단지 수
학의 일부일 뿐입니다.
간단히 말해 머신러닝 모델은 입력을 받고 출력을 반환하는 수학 함수입니다. 따라서 다음과
같이 작성할 수 있습니다.
y(x)f=
함수
f
가 무엇인지 알아내는 과정이 곧 모델이 훈련을 하는 과정입니다.
심층 신경망의 배후에 있는 수학을 소개하기 위해 패션 데이터 예제인
Fashion
-
MNIST
를
사용하겠습니다. 이 데이터셋은 머신러닝 모델 실험과 벤치마킹을 위해 온라인으로 제공합
니다.
TIP
_
인공 신경망의 보편성
기존 머신러닝 기술과 비교해볼 때 심층 신경망 모델이 차별화되는 주된 요소는 심층 신경망이 ‘일반적인’ 경
우에도 적용 가능하다는 것입니다. 즉, 함수가 아무리 복잡하더라도 모든 함수의 정확한 근사치를 나타낼 수
있는 신경망이 있습니다. 심층 신경망이 보편성 원칙을 준수하는 데는 은닉층 하나로 충분합니다.
Fashion
-
MNIST
는
28
×
28
픽셀 해상도의
70
,
000
개 회색조 이미지로 이루어졌습니다. ...
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.