유로 매우 큰 훈련 세트에서는 아주 느립니다(잠시 후에 훨씬 빠른 경사 하강법 알고리즘을 볼 것입니다). 그
러나 경사 하강법은 특성 수에 민감하지 않습니다. 수십만 개의 특성에서 선형 회귀를 훈련시키려면 정규방
정식보다 경사 하강법을 사용하는 편이 훨씬 빠릅니다.
위로 향하는 그래디언트 벡터가 구해지면 반대 방향인 아래로 가야 합니다.
θ
에서
)
(
θ
θ
MSE
∇
를 빼야 한다는 뜻입니다. 여기서 학습률
η
가 사용됩니다.
16
내려가는 스텝의 크기를 결정하기
위해 그래디언트 벡터에
η
를 곱합니다(식
4
-
7
).
식
4-7
경사 하강법의 스텝
)
(
)next step(
θηθ
θ
θ
MSE∇−=
이 알고리즘을 간단히 구현해보겠습니다.
eta
=
0
.
1
#
학습률
n
_
iterations
=
1000
m
=
100
theta
=
np
.
random
.
randn ...
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.
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.
Head of Cybersecurity
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.
Field Engineer
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.
Data Platform Tech Lead
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.