March 2026
Intermediate
504 pages
11h 26m
Korean
Content preview from 파이토치로 배우는 LLM & AI
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.
217
7
장
자연어 처리를 위한 순환 신경망
에폭
훈련 정확도
검증 정확도
정확도
그림
7-17
더 낮은 학습률(
0
.
00001
)을 사용했을 때 정확도
에폭
훈련 손실
검증 손실
손실
그림
7-18
더 낮은 학습률(
0
.
00001
)을 사용했을 때 손실
드롭아웃 사용하기
학습률 매개변수를 바꾸는 것 외에도
LSTM
층에 드롭아웃을 적용하는 방법도 고려해 볼 가치
가 있습니다. 순환 층에서 드롭아웃은 밀집 층과 동일하게 작동합니다.
3
장에서 설명한 것처럼
인접한 뉴런이 비슷해져 학습에 영향을 미치는 것을 방지하기 위해 뉴런을 랜덤하게 제외시킵
218
1
부
모델 구축
니다. 하지만 너무 낮게 설정하지 않도록 주의해야 합니다. 아키텍처가 너무 달라지면 신경망
의 학습 능력을 동결시킬 수 있기 때문입니다.
드롭아웃은
nn
.
Dropout
층을 사용하여 구현할 수 있습니다. 예를 들면 다음과 같습니다.
self.embedding_dropout = nn.Dropout(dropout_rate)
self.lstm_dropout = nn.Dropout(dropout_rate)
self.final_dropout = nn.Dropout ...
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.