May 2020
Beginner to intermediate
952 pages
24h 11m
Korean
Content preview from 핸즈온 머신러닝(2판): 사이킷런, 케라스, 텐서플로 2를 활용한 머신러닝, 딥러닝 완벽 실무
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.
722
2
부
신경망과 딥러닝
이 잘 들어맞는 작업의 사례가 많습니다. 예를 들면 자율주행 자동차나 추천 시스템, 웹 페이지
에 광고를 배치하기
8
, 이미지 분류 시스템이 주의를 집중할 곳을 제어하기 등입니다.
18.2
정책 탐색
소프트웨어 에이전트가 행동을 결정하기 위해 사용하는 알고리즘을
정책
policy
이라고 합니다. 예
를 들어 관측을 입력으로 받고 수행할 행동을 출력하는 신경망이 정책이 될 수 있습니다(그림
18
-
2
).
에이전트 환경
정책
행동
보상 & 관측
그림
18-2
신경망 정책을 사용한 강화 학습
정책은 생각할 수 있는 어떤 알고리즘도 될 수 있으며 결정적일 필요가 없습니다. 사실 어떤 경
우에는 환경을 관측할 필요도 없습니다! 예를 들어
30
분 동안 수집한 먼지의 양을 보상으로 받
는 로봇 진공청소기를 생각해봅시다. 이 청소기의 정책은 매 초마다 어떤 확률
p
만큼 전진하는
것일 수도 있고, (
1
-
p
)의 확률로 왼쪽 또는 오른쪽으로 랜덤하게 회전하는 것일 수도 있습니
다. 회전 각도는 -
r
과 +
r
사이의 랜덤한 각도일 수 있습니다. 이 정책에는 무작위성이 포함되
어 있기 때문에
확률적 정책
stochastic
policy
이라고 합니다. 로봇이 도달할 수 있는 어떤 장소라도 모
두 찾아서 먼지를 수집하려고 이상한 궤적을 만들어낼 것입니다. 궁금한 것은 ‘
30
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.