August 2024
Beginner to intermediate
640 pages
14h 53m
Korean
Content preview from AI를 위한 필수 수학
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.
369
Chapter 9 -
그래프 모델
핀을 추천할 수 있었다. 핀세이지 그래프 합성곱 신경망 모델은 그래프에서 랜덤 워크를 활용
하는데, 이에 대해서는
Chapter
9
의 후반부에서 설명한다. 다음은 논문의 초록이다.
최근 그래프 구조의 데이터를 위한 심층 신경망의 발전으로 추천 시스템 벤치마크에서 최첨단 성능을 달성
할 수 있게 되었다. 하지만 이러한 방법을 수십억 개의 항목과 수억 명의 사용자가 있는 웹 스케일
Web
-
scale
의
추천 시스템에 대해 실용적이고 확장 가능하게 만드는 것은 여전히 어려운 과제다. 여기서는 핀터레스트에
서 개발하고 배포한 대규모 심층 추천 엔진에 대해 설명한다. 효율적인 랜덤 워크와 그래프 합성곱을 결합하
여 그래프 구조와 노드 피처 정보를 모두 포함한 노드의 임베딩을 생성하는 효율적인 그래프 합성곱 신경망
(
GCN
) 알고리즘인 핀세이지를 개발했다. 합성곱을 구조화하기 위한 매우 효율적인 랜덤 워크를 토대로 새
로운 방법을 개발했고, 모델의 견고함과 수렴성을 개선하기 위해 점점 더 어려운 훈련 데이터에 기반을 둔 새
로운 훈련 전략을 설계했다. 그리고 핀터레스트에 핀세이지를 배포하고 핀과 보드를 나타내는
30
억 개의 노
드와
180
억 개의 엣지로 구성된 그래프에서
75
억 개의 예제를 학습시켰다. 오프라인 지표, 사용자 연구 및 ...
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.