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.
90
1
부
인공지능을 속이는 기술
능하게 합니다.
이미지나 오디오와 마찬가지로 신경망을 사용하지 않고 영상을 처리하는 더 고전적인 접근방
식도 있습니다. 그러나 심층 신경망을 사용하면 특성 추출 규칙을 직접 코딩하지 않아도 됩
니다.
당연히 시간이라는 요소는 프레임 처리에 복잡성을 추가합니다. 그러나
CNN
과
RNN
에 대해
앞에서 설명한 구조 원칙을 사용해 이러한 추가 차원을 처리하는 방법이 있습니다. 예를 들면,
‘
3D
합성곱’을 이용하는 방법입니다. 이미지
CNN
에 사용한 합성곱 원리를 확장하면 각 프레
임 내의 공간 차원과 동일한 방식으로 처리되는 프레임에 걸친 제
3
의 시간 차원이 포함됩니다.
아니면
CNN
의 공간 학습을
RNN
아키텍처에서 차용한 순차적 학습과 결합하는 것도 가능합
니다. 이는
CNN
을 이용해 프레임 단위로 특성을 추출한 다음, 특성을
RNN
의 순차적 입력으
로 사용해 수행할 수 있습니다.
컬러 이미지가
4D
텐서로 신경망에 전달된다면, 영상 입력은 무려
5D
텐서로 표현됩니다. 예
를 들어 초당
15
프레임의
1
분 분량의 동영상을 샘플링하면
900
프레임이 됩니다.
RGB
채널을
사용하는 저해상도 영상 (
224
×
224
픽셀 )과 색상을 가정해봅시다. 우리는 다음과 같은 모양의
4D
텐서를 가지고 있습니다.
shape = (900, 224,
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.