aquachieh
    • Create new note
    • Create a note from template
      • Sharing URL Link copied
      • /edit
      • View mode
        • Edit mode
        • View mode
        • Book mode
        • Slide mode
        Edit mode View mode Book mode Slide mode
      • Customize slides
      • Note Permission
      • Read
        • Only me
        • Signed-in users
        • Everyone
        Only me Signed-in users Everyone
      • Write
        • Only me
        • Signed-in users
        • Everyone
        Only me Signed-in users Everyone
      • Engagement control Commenting, Suggest edit, Emoji Reply
    • Invite by email
      Invitee

      This note has no invitees

    • Publish Note

      Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note

      Your note will be visible on your profile and discoverable by anyone.
      Your note is now live.
      This note is visible on your profile and discoverable online.
      Everyone on the web can find and read all notes of this public team.
      See published notes
      Unpublish note
      Please check the box to agree to the Community Guidelines.
      View profile
    • Commenting
      Permission
      Disabled Forbidden Owners Signed-in users Everyone
    • Enable
    • Permission
      • Forbidden
      • Owners
      • Signed-in users
      • Everyone
    • Suggest edit
      Permission
      Disabled Forbidden Owners Signed-in users Everyone
    • Enable
    • Permission
      • Forbidden
      • Owners
      • Signed-in users
    • Emoji Reply
    • Enable
    • Versions and GitHub Sync
    • Note settings
    • Note Insights
    • Engagement control
    • Transfer ownership
    • Delete this note
    • Save as template
    • Insert from template
    • Import from
      • Dropbox
      • Google Drive
      • Gist
      • Clipboard
    • Export to
      • Dropbox
      • Google Drive
      • Gist
    • Download
      • Markdown
      • HTML
      • Raw HTML
Menu Note settings Versions and GitHub Sync Note Insights Sharing URL Create Help
Create Create new note Create a note from template
Menu
Options
Engagement control Transfer ownership Delete this note
Import from
Dropbox Google Drive Gist Clipboard
Export to
Dropbox Google Drive Gist
Download
Markdown HTML Raw HTML
Back
Sharing URL Link copied
/edit
View mode
  • Edit mode
  • View mode
  • Book mode
  • Slide mode
Edit mode View mode Book mode Slide mode
Customize slides
Note Permission
Read
Only me
  • Only me
  • Signed-in users
  • Everyone
Only me Signed-in users Everyone
Write
Only me
  • Only me
  • Signed-in users
  • Everyone
Only me Signed-in users Everyone
Engagement control Commenting, Suggest edit, Emoji Reply
  • Invite by email
    Invitee

    This note has no invitees

  • Publish Note

    Share your work with the world Congratulations! 🎉 Your note is out in the world Publish Note

    Your note will be visible on your profile and discoverable by anyone.
    Your note is now live.
    This note is visible on your profile and discoverable online.
    Everyone on the web can find and read all notes of this public team.
    See published notes
    Unpublish note
    Please check the box to agree to the Community Guidelines.
    View profile
    Engagement control
    Commenting
    Permission
    Disabled Forbidden Owners Signed-in users Everyone
    Enable
    Permission
    • Forbidden
    • Owners
    • Signed-in users
    • Everyone
    Suggest edit
    Permission
    Disabled Forbidden Owners Signed-in users Everyone
    Enable
    Permission
    • Forbidden
    • Owners
    • Signed-in users
    Emoji Reply
    Enable
    Import from Dropbox Google Drive Gist Clipboard
       owned this note    owned this note      
    Published Linked with GitHub
    2
    Subscribed
    • Any changes
      Be notified of any changes
    • Mention me
      Be notified of mention me
    • Unsubscribe
    Subscribe
    # [2025李宏毅ML] 第1講:一堂課搞懂生成式人工智慧的技術突破與未來發展 :::success :+1: 筆記全集Book 請至: https://hackmd.io/@4j/r1U_UJ_pye/ ::: :::info 2025生成式AI時代下的機器學習_李宏毅 課程網站 https://speech.ee.ntu.edu.tw/~hylee/ml/2025-spring.php video: https://www.youtube.com/watch?v=QLiKmca4kzI pdf: https://speech.ee.ntu.edu.tw/~hylee/ml/ml2025-course-data/introduction.pdf ::: :::spoiler 目錄 [TOC] ::: 請回顧精華片段 ![image](https://hackmd.io/_uploads/Sk6r4zqq1e.png =500x) "想投影片的內容" 才是最花時間的!!(老師不可取代的地方) ![image](https://hackmd.io/_uploads/HkpKuzcqkg.png =500x) ## 思考(Reasoning) 像是腦內小劇場 ![image](https://hackmd.io/_uploads/S1Uodfcqyl.png =500x) ▪ AI Agent ![image](https://hackmd.io/_uploads/H17f1m951g.png =500x) Deep Research 也有點 AI Agent 的能力 隨著搜尋到的結果不同 改變要搜尋的內容 ## 運作機制 ![image](https://hackmd.io/_uploads/SkVTw8Jjyg.png =500x) ==> 複雜物件 由 **有限的**基本單位 構成 多個有限的選擇 可組合成近乎無窮的可能 基本單位可能是文字、像素、取樣點等 token ![image](https://hackmd.io/_uploads/rkyyu81j1x.png =500x) 策略:根據固定的次序每次只產生一個 yi 稱作 **Autoregressive Generation** (像文字接龍) ![image](https://hackmd.io/_uploads/Bk3G_IyiJe.png =500x) 給一串token, 決定下一個token(的機率分佈)(選擇題) 也可把多模態的 token 集合起來生成 ▪ 怎麼決定下一個 token 答案往往不是唯一 故讓他產生機率分布 再去擲骰子決定答案(每次輸出可能不同) ![image](https://hackmd.io/_uploads/rkdUr_1oyg.png =500x) 深度學習:多個Layer ![image](https://hackmd.io/_uploads/ByGvrOJsJl.png =500x) ![image](https://hackmd.io/_uploads/BJMdHdJo1e.png =500x) 深度學習:像是把 複雜問題 拆解成簡單問題(多個步驟) 反而更有效率 ref: https://www.youtube.com/watch?v=KKT2VkTdFyc ![image](https://hackmd.io/_uploads/r1XtK_JsJx.png =500x) 困難的問題需要思考很多步,Layer 不夠 ==> **深度不夠,長度來湊** (Testing Time Scaling) ![image](https://hackmd.io/_uploads/SkLbsuyikg.png =500x) ![image](https://hackmd.io/_uploads/Hk_zsdJsJg.png =500x) 一個layer裡有很多小layer,有考慮 全局/單點 的 **Self-attention Layer**: 產生輸出時,會考慮全部的輸入 ![image](https://hackmd.io/_uploads/Sk5msuksye.png =500x) 含有 Self-attention Layer 的 通常稱為 **Transformer** ![image](https://hackmd.io/_uploads/BJOVsuJiyg.png =500x) ▪ Transformer 的限制? 輸入無法太長 運作會有問題 出現改良版的架構 ==> **Mamba** ![image](https://hackmd.io/_uploads/HyDSsuyokl.png =500x) ## 運作機制是怎麼產生出來的 ![image](https://hackmd.io/_uploads/HyjSJ2ei1l.png =500x) ▪ **架構 architecture** 超參數 (hyperparameter) <-- 所謂的調參數 由開發者(人類)決定 天生資質 ▪ **參數 parameter** 由訓練資料決定 後天學習 ![image](https://hackmd.io/_uploads/BkOmenxjyg.png =500x) 尋找能讓 𝑓𝜃 最能滿足 訓練資料的參數𝜃 ### 通用機器學習模型 "通用" 在歷史上有不同的含義 ![image](https://hackmd.io/_uploads/ByTcenxs1e.png =500x) ▪ **通用機器學習模型:第一型態 (2018-2019)** 僅是個 decoder, 無法直接用 後面需要再外掛一個特化模型才能達到目的 ex: 芝麻街家族模型 ![image](https://hackmd.io/_uploads/HJZYzhljyg.png =500x) ▪ **通用機器學習模型:第二型態 (2020-2022)** 有完整的文字生成功能 但無法用指令操控他 需再微調一下參數 把模型用在不同任務上屬於: 架構相同、參數不同 ![image](https://hackmd.io/_uploads/SJctGhlikg.png =500x) ▪ **通用機器學習模型:第三型態 (2023)** 用在不同任務上時,不需再做模型的調整,直接下指令即可 ![image](https://hackmd.io/_uploads/SJv5f2gikg.png =500x) 回顧 ref: Pre-train https://youtu.be/cCpErV7To2o?s Fine-tune https://youtu.be/Q9cNkUPXUB8?s RLHF https://youtu.be/v12IKvF6Cj8? ## 怎麼賦予新的能力 機器的終身學習(Life-long Learning)時代 ![image](https://hackmd.io/_uploads/HyYTZ6eiJl.png =500x) ![image](https://hackmd.io/_uploads/ByX1Gaxs1l.png =500x) prompt的調整(給他需求資訊) 此種模型的參數是固定的 不會永遠改變行為 (一旦移除指令 他就會復原) ![image](https://hackmd.io/_uploads/B1q7MTgjyx.png =500x) 若希望他永久具備新技能 --> 就需 **改變參數** ▪ **微調(fine-tune)** 要注意可能使原始能力下降 不是個容易事 是最後的手段! (提醒:應該先確定不微調就無法具備目標能力,才選擇微調) ![image](https://hackmd.io/_uploads/Hy2vfagoye.png =500x) ChatGPT有介面可輸入資料 微調參數 https://platform.openai.com/docs/guides/fine-tuning ![image](https://hackmd.io/_uploads/HyvQN6ejJx.png =500x) 微調 可能使模型原始的能力錯亂 Q:我們只想要改基礎模型的一個小地方 有必要麻煩到去微調參數嗎? ![image](https://hackmd.io/_uploads/BkbJS6li1g.png =500x) ▪ **模型編輯(Model Editing)/ 類神經網路編輯** 直接找出有關的參數 人工手動修改! ref: 第八講 作業八 ![image](https://hackmd.io/_uploads/rkh1rpxokx.png =500x) ▪ **Model Merging** 在沒有訓練資料下 直接合體兩個模型的能力 ref: 第九講 作業九 ![image](https://hackmd.io/_uploads/Sy6eSTxskl.png =500x) -- END --

    Import from clipboard

    Paste your markdown or webpage here...

    Advanced permission required

    Your current role can only read. Ask the system administrator to acquire write and comment permission.

    This team is disabled

    Sorry, this team is disabled. You can't edit this note.

    This note is locked

    Sorry, only owner can edit this note.

    Reach the limit

    Sorry, you've reached the max length this note can be.
    Please reduce the content or divide it to more notes, thank you!

    Import from Gist

    Import from Snippet

    or

    Export to Snippet

    Are you sure?

    Do you really want to delete this note?
    All users will lose their connection.

    Create a note from template

    Create a note from template

    Oops...
    This template has been removed or transferred.
    Upgrade
    All
    • All
    • Team
    No template.

    Create a template

    Upgrade

    Delete template

    Do you really want to delete this template?
    Turn this template into a regular note and keep its content, versions, and comments.

    This page need refresh

    You have an incompatible client version.
    Refresh to update.
    New version available!
    See releases notes here
    Refresh to enjoy new features.
    Your user state has changed.
    Refresh to load new user state.

    Sign in

    Forgot password

    or

    By clicking below, you agree to our terms of service.

    Sign in via Facebook Sign in via Twitter Sign in via GitHub Sign in via Dropbox Sign in with Wallet
    Wallet ( )
    Connect another wallet

    New to HackMD? Sign up

    Help

    • English
    • 中文
    • Français
    • Deutsch
    • 日本語
    • Español
    • Català
    • Ελληνικά
    • Português
    • italiano
    • Türkçe
    • Русский
    • Nederlands
    • hrvatski jezik
    • język polski
    • Українська
    • हिन्दी
    • svenska
    • Esperanto
    • dansk

    Documents

    Help & Tutorial

    How to use Book mode

    Slide Example

    API Docs

    Edit in VSCode

    Install browser extension

    Contacts

    Feedback

    Discord

    Send us email

    Resources

    Releases

    Pricing

    Blog

    Policy

    Terms

    Privacy

    Cheatsheet

    Syntax Example Reference
    # Header Header 基本排版
    - Unordered List
    • Unordered List
    1. Ordered List
    1. Ordered List
    - [ ] Todo List
    • Todo List
    > Blockquote
    Blockquote
    **Bold font** Bold font
    *Italics font* Italics font
    ~~Strikethrough~~ Strikethrough
    19^th^ 19th
    H~2~O H2O
    ++Inserted text++ Inserted text
    ==Marked text== Marked text
    [link text](https:// "title") Link
    ![image alt](https:// "title") Image
    `Code` Code 在筆記中貼入程式碼
    ```javascript
    var i = 0;
    ```
    var i = 0;
    :smile: :smile: Emoji list
    {%youtube youtube_id %} Externals
    $L^aT_eX$ LaTeX
    :::info
    This is a alert area.
    :::

    This is a alert area.

    Versions and GitHub Sync
    Get Full History Access

    • Edit version name
    • Delete

    revision author avatar     named on  

    More Less

    Note content is identical to the latest version.
    Compare
      Choose a version
      No search result
      Version not found
    Sign in to link this note to GitHub
    Learn more
    This note is not linked with GitHub
     

    Feedback

    Submission failed, please try again

    Thanks for your support.

    On a scale of 0-10, how likely is it that you would recommend HackMD to your friends, family or business associates?

    Please give us some advice and help us improve HackMD.

     

    Thanks for your feedback

    Remove version name

    Do you want to remove this version name and description?

    Transfer ownership

    Transfer to
      Warning: is a public team. If you transfer note to this team, everyone on the web can find and read this note.

        Link with GitHub

        Please authorize HackMD on GitHub
        • Please sign in to GitHub and install the HackMD app on your GitHub repo.
        • HackMD links with GitHub through a GitHub App. You can choose which repo to install our App.
        Learn more  Sign in to GitHub

        Push the note to GitHub Push to GitHub Pull a file from GitHub

          Authorize again
         

        Choose which file to push to

        Select repo
        Refresh Authorize more repos
        Select branch
        Select file
        Select branch
        Choose version(s) to push
        • Save a new version and push
        • Choose from existing versions
        Include title and tags
        Available push count

        Pull from GitHub

         
        File from GitHub
        File from HackMD

        GitHub Link Settings

        File linked

        Linked by
        File path
        Last synced branch
        Available push count

        Danger Zone

        Unlink
        You will no longer receive notification when GitHub file changes after unlink.

        Syncing

        Push failed

        Push successfully