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.
107
5
장
적대적 입력의 원리
NOTE
_
예제 코드: 임의 데이터로 하는 실험
이 책의 깃허브에 있는 주피터 노트북(
chapter05
/
fashion
‐
MNIST
_
random
_
images
.
ipynb
)을 이용해
임의의 이미지를 사용한
Fashion
-
MNIST
분류 테스트를 할 수 있습니다.
모델을 개선하기 위해서 임의의 픽셀과 ‘미분류’ 라벨을 추가해 구성한 훈련 이미지로 다시 훈련합니다. 주피
터 노트북에는 이 작업을 수행하는 코드도 수록되었습니다.
주피터 노트북(
chapter05
/
resnet50
_
random
_
images
.
ipynb
)은 임의의 데이터에
ResNet50
을 테스
트할 수 있는 코드를 제공합니다.
[그림
5
-
4
]에서
Fashion
-
MNIST
는 임의의 이미지를 ‘가방’으로 확신 있게 예측(
0
.
850
)하고
분류기에 전달된 임의의 픽셀 이미지의
99
% 이상을 이렇게 분류할 것입니다. 이는 모델이 입
력 공간의 대부분을 ‘가방’으로 분류하는 방법을 배웠음을 나타냅니다. ‘가방’ 이미지가 특정 픽
셀로 식별되는 것이 아니라 어떤 다른 분류에도 속하지 않는다는 사실을 기반으로 결정되는 것
같습니다. 적어도
ResNet50
은 확신 있는 분류를 반환하지 않으므로 임의의 이미지를 잘못 식
별하지 않았습니다.
5.2
DNN
의 사고를 가능하게 하는 원리
DNN
을 설명하는
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.