저자에게 이메일 보내기

You can use this page to email Afshine Amidi, Shervine Amidi, 그리고 Yongjin Kim about Super Study Guide: 트랜스포머와 대형 언어 모델.

Please include an email address so the author can respond to your query

This message will be sent to Afshine Amidi, Shervine Amidi, 그리고 Yongjin Kim

This site is protected by reCAPTCHA and the Google  Privacy Policy and  Terms of Service apply.

도서 소개

이 책은 면접 준비, 프로젝트 진행, 또는 순수한 지적 호기심을 위해 대규모 언어 모델의 내부 구조와 작동 원리를 이해하고 싶은 모든 분들을 위한, 그림으로 설명하는 핵심 가이드입니다.

이 책은 총 5개의 파트로 구성되어 있습니다:

  • 기초: 신경망 입문부터 훈련, 평가에 필요한 핵심 딥러닝 개념까지
  • 임베딩: 토큰화 알고리즘, 단어 임베딩(word2vec), 그리고 문장 임베딩(RNN, LSTM, GRU)
  • 트랜스포머: 셀프 어텐션 메커니즘의 등장 배경, 인코더-디코더 구조의 상세한 분석, 그리고 BERT, GPT, T5와 같은 대표 모델들
  • 대형 언어 모델: 최고 성능을 내는 최신 모델들, 프롬프트 엔지니어링 팁, 그리고 미세 조정(SFT, PEFT)과 선호도 튜닝(RLHF, DPO)을 통한 모델 최적화 방법
  • 응용: 감성 추출, 기계 번역, 문서 요약, 검색 증강 생성(RAG) 등 다양한 실제 적용 사례

저자 소개

Afshine Amidi’s avatar Afshine Amidi

@afshinea

Afshine Amidi is currently teaching the Transformers & Large Language Models workshop at Stanford and is also leading LLM efforts at Netflix. Previously, he worked on the Gemini team at Google and used NLP techniques to solve complex queries. Before that, he worked at Uber Eats to improve the quality of the search and recommendation systems. On the side, Afshine published a few papers at the intersection of deep learning and computational biology. He holds a Bachelor’s and a Master’s Degree from École Centrale Paris and a Master’s Degree from MIT.

Shervine Amidi’s avatar Shervine Amidi

@shervinea

Shervine Amidi is currently teaching the Transformers & Large Language Models workshop at Stanford and is also working on the Gemini team at Google to leverage LLMs for action-based queries. Previously, he worked on applied machine learning problems for recommender systems at Uber Eats where he focused on representation learning to better surface dish recommendations. On the side, Shervine published a few papers at the intersection of deep learning and computational biology. He holds a Bachelor’s and a Master’s Degree from École Centrale Paris and a Master’s Degree from Stanford University.

Yongjin Kim’s avatar Yongjin Kim

Logo white 96 67 2x

Publish Early, Publish Often

  • Path
  • There are many paths, but the one you're on right now on Leanpub is:
  • Transformers-daehyeong-eoneo-model › Email Author › New
    • READERS
    • Newsletters
    • Weekly Sale
    • Monthly Sale
    • Store
    • Home
    • Redeem a Token
    • Search
    • Support
    • Leanpub FAQ
    • Leanpub Author FAQ
    • Search our Help Center
    • How to Contact Us
    • FRONTMATTER PODCAST
    • Featured Episode
    • Episode List
    • MEMBERSHIPS
    • Reader Memberships
    • Department Reader Memberships
    • Author Memberships
    • Your Membership
    • COMPANY
    • About
    • About Leanpub
    • Blog
    • Contact
    • Press
    • Essays
    • AI Services
    • Imagine a world...
    • Manifesto
    • More
    • Partner Program
    • Causes
    • Accessibility
    • AUTHORS
    • Write and Publish on Leanpub
    • Create a Book
    • Create a Bundle
    • Create a Course
    • Create a Track
    • Testimonials
    • Why Leanpub
    • Services
    • Author Quickstart (NEW!)
    • TranslateAI
    • PublishWord
    • Publish on Amazon
    • CourseAI
    • GlobalAuthor
    • Marketing Packages
    • IndexAI
    • Author Newsletter
    • The Leanpub Author Update
    • Author Support
    • Author Help Center
    • Leanpub Authors Forum
    • The Leanpub Manual
    • Supported Languages
    • The LFM Manual
    • Markua Manual
    • API Docs
    • Organizations
    • Learn More
    • Sign Up
    • LEGAL
    • Terms of Service
    • Copyright Policy
    • Privacy Policy
    • Refund Policy

*   *   *

Leanpub is copyright © 2010-2025 Ruboss Technology Corp.
All rights reserved.

This site is protected by reCAPTCHA
and the Google  Privacy Policy and  Terms of Service apply.

Leanpub requires cookies in order to provide you the best experience. Dismiss