January 2017
Beginner to intermediate
312 pages
7h 3m
Korean
Content preview from 밑바닥부터 시작하는 딥러닝
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.
136
밑바닥부터 시작하는 딥러닝
참고로 이 구현에서는 새로운 함수를 정의하는 데 “
def
f
(
x
):...” 문법을 썼는데, 파이썬에서는
간단한 함수라면 람다
lambda
기법을 쓰면 더 편합니다. 가령
lambda
를 쓰면 다음과 같이 구현
할 수 있습니다.
>>>
f
=
lambda w
:
net
.
loss
(
x
,
t
)
>>>
dW
=
numerical
_
gradient
(
f
,
net
.
W
)
신경망의 기울기를 구한 다음에는 경사법에 따라 가중치 매개변수를 갱신하기만 하면 됩니다.
다음 절에서는
2
층 신경망을 대상으로 학습 과정 전체를 구현합니다.
여기에서 사용한
numerical
_
gradient
( )는 가중치 매개변수
W
가 다차원 배열을 처리할 수 있도
록 앞의 구현에서 조금 수정했습니다. 다차원 배열 처리 외에는 수정하지 않았으니 설명은 생략하겠습니다.
자세히 알고 싶은 분은 소스 코드 (
common
/
gradient
.
py
)를 참고하세요.
4.5
학습 알고리즘 구현하기
신경망 학습에 관한 기본적인 지식은 이만하면 충분합니다. ‘손실 함수’, ‘미니배치’, ‘기울기’,
‘경사 하강법’ 등의 중요한 키워드가 연달아 등장해서 숨 가쁘셨죠? 복습도 할 겸, 신경망 학습
의 순서를 확인해보죠. 자, 신경망 학습의 절차는 다음과 같습니다.
전제
신경망에는 적응 가능한 가중치와 편향이 ...
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.