May 2018
Beginner to intermediate
672 pages
16h 54m
Korean
Content preview from 핸즈온 머신러닝: 사이킷런과 텐서플로를 활용한 머신러닝, 딥러닝 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.
611
부록 A
연습문제 정답
층과 출력층에서 사용하는 활성화 함수입니다.
8
일반적으로
ReLU
(또는 이 함수의 변종.
11
장 참조 )가 은닉층의 활성화 함수 기본값으로 좋습니다. 출력층에서는 일반적으로 이진
분류에서는 로지스틱 활성화 함수, 다중 분류에서는 소프트맥스 활성화 함수를 사용하고
회귀에서는 활성화 함수를 적용하지 않습니다.
MLP
가 훈련 데이터에 과대적합되었다면 은닉층 수와 각 은닉층에 있는 뉴런 수를 줄여볼
수 있습니다.
9
.
https
://
github
.
com
/
rickiepark
/
handson
-
ml
/
에 있는 주피터 노트북을 참고하세요.
11
장
:
심층 신경망 훈련
1
.
아니오. 모든 가중치는 독립적으로 샘플링되어야 합니다. 즉, 같은 초깃값을 가지면 안 됩
니다. 가중치를 무작위로 샘플링하는 중요한 한 가지 목적은 대칭성을 피하기 위함입니다.
모든 가중치가
0
이 아니더라도 같은 초깃값을 가지면 대칭성이 깨지지 않고(즉, 어떤 층
에 있는 모든 뉴런이 동일합니다 ) 역전파도 이를 해결할 수 없을 것입니다. 구체적으로 말
하면 어떤 층에 있는 모든 뉴런이 항상 같은 가중치를 가지게 됩니다. 이는 층마다 하나의
뉴런이 있는 것과 같으므로 수렴하는 데 오랜 시간이 걸립니다. 이런 구성으로 좋은 솔루
션에 수렴하는 것은 사실상 불가능합니다.
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.