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.
61
3
장
심층 신경망
:
.
.
.
.
0 232
0 119
0 151
0 005
p
f
이미지와 관련된 대상 라벨은 벡터의 두 번째 값에 해당하는 ‘
Trouser
’입니다. 이상적으로 이
값은 현재의 값
0
.
119
가 아니라
1
에 가까워야 합니다. 신경망이 완벽하게 잘 수행되었다면 예
측 벡터를 반환했을 것입니다.
:
0
1
0
0
f
p
이 예제의 계산된 비용은 목표 벡터와 라벨 예측 간 차이의 제곱입니다.
::
.
.
.
.
....
..
0 032
0 119
0 151
0 005
0
1
0
0
0 001 0 776 0 023 0 000
2
-=++
++
ff
f
p
p
p
이 경우 바지 분류의 비용이 높음을 알 수 있습니다. 따라서 이 문제를 해결하려면 신경망의 일
부 매개변수를 조정해야 합니다.
그러나 신경망의 성능을 실제로 평가하려면 모든 훈련 예제의 비용을 고려해야 합니다. 전체
성능을 측정하는 한 가지 방법은 평균 비용을 계산하는 것입니다. 이 계산은 손실 함수를 제공
하는데, 이 함수는 모든 오류의 제곱 평균을 취해 평균 제곱 오차 (
MSE
)라고 합니다.
다른 손실 함수는 다른 알고리즘을 사용해 훈련 중 손실을 계산합니다. 분류 모델의 경우 일반
62
1
부
인공지능을 속이는 기술
적으로 ‘범주형 교차 엔트로피’ 손실 함수를 사용합니다. 이 함수는 네트워크가 더 높은 신뢰도
로 반환하는 오류를 줄이는 데 더 좋습니다.
3
장
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.