張星瑀 Sheena
    • 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
    Subscribed
    • Any changes
      Be notified of any changes
    • Mention me
      Be notified of mention me
    • Unsubscribe
    Subscribe
    # 深度學習簡介 ## 工業4.0帶來的影響 提到智慧管理、智慧製造等,就不得不提到當初由德國提出的「工業4.0」。若說第三代工業的重點在於改良上一代以「大量生產」為主軸的產業分工、電力應用,進而實現自動化、電子化和高效生產的製造技術;那麼第四代工業就是將這些工業生產過程,更進一步透過: * 網路物理系統Cyber Physical System * 物聯網IoT * 人工智慧AI **· · ·** 來減少工業中的成本(如:生產成本、勞動人力成本、維護成本等)。這些科技的技術發展,強調數據的重要性,以輔助人類在生產過程中的效率與品質。例如,在工業3.0中電子革命帶來的便捷性、通訊功能,使得自動化的生產得以被實現,透過網路又能為企業進行電子商務、財務管理、交易等。而工業4.0就是在這些技術基礎上使用一些智慧技術(大數據、物聯網、機器學習等),協助生產過程中的數據分析及即時回饋,換句話說,如果上一個時代是讓機器長出自己的手,那工業4.0就是給機器一顆會自己思考的腦,讓它嘗試透過蒐集到的狀況、數據,做出合理判斷,甚至是能自主地解決一些問題。因此,這些也是為什麼智慧製造、智慧管理得以被討論的原因。[1] 在這裡不得不提到深度學習在工業4.0所扮演的角色啦🤗,不過在此之前!筆者還是要小小地介紹一下深度學習到底是什麼? ### AI(人工智慧)?機器學習?深度學習?GPT-4? >筆者在上大學之前,對於科技只知道有神經網路、人工智慧、演算法諸如此類的名稱,但完全對它們不熟悉,甚至一度以為都是同一個東西——總之就是很厲害很難的程式之類的吧!現在看來我真的是菜鳥一隻very NAIVE;-)。不過能找出自己的盲點再不斷修正,才是學習的目標~所以,以下的一小節僅針對筆者不了解的專有名詞做整理。**若以下有誤,歡迎留言提點🙏謝謝**! ## **🖥人工智慧Artificial Intelligence(AI)** 在20世紀50年代時,人們讓電腦透過一些計算方法、邏輯及規則,期許能讓擁有「人的智慧」,這時期設計AI主要以「規則主導」,而最後結果沒有很成功。隨著記憶體、晶片的蓬勃發展、硬體設備成本降低,電腦的運算能力也逐漸變好,專家針對機器以什麼方式學習和理解知識有更多的研究機會,才逐步發展到現在的樣子。用ChatGPT這AI技術自己的話來說就是: >**人工智慧(AI)是指通過計算機系統模擬和模仿人類智能的能力。** 簡單來說,AI是一個廣泛的領域,旨在使計算機具有類似於人類的思維、學習、問題解決和決策能力。 [color=#586D80] >[name=Chat GPT] ## **🤖機器學習Machine Learning(ML)** 機器學習是AI的子集,它主要是為了解決某個特定的(具線性結果的)問題而設計出來的。**ML透過統計技術從過去所觀察的結果特徵**,再進一步對未來相似的情況做行動。這個學習過程,仍需仰賴ML設計者餵給機器的資訊。例如,若要讓機器判斷右邊的卡戴珊姐妹照中誰是Kylie?誰是Kim?設計者需要提前將這兩個人的特徵告訴機器,讓它先學習什麼是「臉比較寬」,再讓機器依著分析完的圖像值,進行分類。 ![](https://hackmd.io/_uploads/B17hVeTJ6.png) 🔼粉色框框中為設計者提供的人物對應的臉部特徵表,經由ML的Classification,即得出結論是「左邊為Kylie」。 ## 小小體驗Teachable Machine 以下是筆者大一通識課中玩的機器學習網站,它是由Google開發的AI實驗: >**Teachable Machine:** https://teachablemachine.withgoogle.com/ [color=#586D80] 這個網站的操作界面平易近人且教學完整,基本上就是在class中增加樣本圖像(盡量選可以畫面只有樣本主題的),你可以為這個class命名,接著根據想分辨的多寡重複增加class。 ![](https://hackmd.io/_uploads/ByX75xTy6.png) 🔺100%的Kylie! ![](https://hackmd.io/_uploads/S1OD9g6yp.png) 🔺只有83%的Kim Kardashian(可能餵的圖片挑得不好,不然就是訓練參數調整不足) >Picture Source: [Kylie Jenner](https://www.cosmopolitan.com/style-beauty/beauty/a19604309/kylie-jenner-blonde-hair-post-baby-makeover/), [Kim Kardashian](https://www.cosmopolitan.com/entertainment/celebs/a39934298/kim-kardashian-platinum-blonde-met-gala-hair-full-look/) and [Kylie and Kim](https://economictimes.indiatimes.com/magazines/panache/kylie-jenner-kim-kardashian-instagrams-two-biggest-stars-urge-meta-owned-app-to-stop-trying-to-be-like-tiktok-could-this-create-trouble/articleshow/93134098.cms?from=mdr) ## **:brain:深度學習Deep Learning(DL)** 深度學習則是機器學習的子集,其訓練模型以深度神經網路為主,機器可以透過大量的數據輸入,自行提取特徵再建立標籤以分類解決問題。DL的應用多為影像辨識、語音辨識、自然語言處理等。 以下參考***Machine Learning vs. Deep Learning: The Ultimate Comparison***, https://www.iteratorshq.com/blog/machine-learning-vs-deep-learning-the-ultimate-comparison/ 所整理出來的建議比對表。 | 深度學習 | 機器學習 | | ---------------------------------------------------------- | ------------------------------------------------------------ | | 訓練時間較短 | 訓練時間較長 | | 創建類神經網路來學習,並根據它自身的演算法做出具智慧的判斷 | 針對輸入資料進行分析與學習,並對它所學的內容進行有根據的判斷 | | 訓練時對GPU有一定的硬體規格要求 | 在CPU上訓練 | ## **💬GPT,欸?** 【放「欸?」的chatgpt】 講到最熟悉的深度學習應用,應該非ChatGPT莫屬,它的誕生對筆者等同儕學生們來說,非常開心!它不僅打破了過去較死板的聊天機器人的對話模式,而且在資料蒐集與整合上也非常強大。不過,ChatGPT只是GPT模型的應用之一,其它有名的應用還有Dall-E(一種付費的文字轉圖片的AI應用網站)。 這些應用都是出於OpenAI的GPT模型所訓練出來的,Generative Pre-trained Transformer(GPT)照著英文名稱直翻就是「生成式預訓練轉換器」(看起來有點難懂😅),可以理解成「用預先訓練的模型來生成的轉換器」。從GPT的歷史演變或許比較好理解這樣的概念: * 首先,得從Transformer這個神經網路架構說起,<font color=" #9297AB">(本章節的重點不是NLP,所以僅短短介紹而已> <)</font>,這種模型有別於過去傳統LSTM(長短期記憶模型)單向且依序的語言處理方式,Transformer有更快速且同步處理的好處,更重要的是模型的訓練會讓它嘗試去學習「什麼是語言?」;像是從小我們學英文會從單字學,當老師教```蘋果is Apple```的時候,也會一定會一起教```橘子is Orange```……然後逐漸地,我們開始學習基礎文法,而且老師教```This is an apple```的話,也會跟著教```That is an orange```。現在,只是把這樣的學習模式轉換成電腦能理解的模式來訓練。 見下圖,當我想翻譯This is good的時候,因為Transformer有Encoder編碼層與Decoder解碼層的區分: 1.在處理時機器會先從英文的```This``` ```is``` ```good```這三個單字做編碼處理(如果詞義越相近的,它們的編碼矩陣值也會更接近),而透過[Multi-Head Self-Attention的機制](https://andy6804tw.github.io/2021/05/03/ntu-multi-head-self-attention/),模型得以同時以不同的組合裡關注這些輸入並對這些組合評分,以觀察組合中的規律、學習這其中的關係,接著針對這些結果進行權重調整。➡這是第一步:學習什麼是This is good. 2.編碼接著進入到Decoder,讓句子從頭(在文法上)有順序的產生輸出。像是第一個單字"This"會得到輸出「這」,而「這」後面可以搭配的內容可能會組成「這個」、「這是」、「這些」· · ·但隨著下一個輸入"is"進來,「這」與"is"的直翻結果「是」就有了相關聯,最後得出「這是」,於是重複這樣的動作,最後就可以得出「這是好的。」的結果了:D➡這是第二步:學習英文單字是如何對應到中文句子。 ![](https://hackmd.io/_uploads/Syudcv6kT.png) 🔺Transformer的建議模型示意圖 >截圖來源:***BERT Neural Network - EXPLAINED!*** by CodeEmporium, https://youtu.be/xI0HHN5XKDo?si=RMHRX7QkDMOXkkL3 它淺顯易懂地介紹了編碼器BERT,影片蠻短的,強烈推薦🤩另外也有一篇文章可以參考**Jay Alammar(2021).*The Illustrated BERT, ELMo, and co. (How NLP Cracked Transfer Learning)*** http://jalammar.github.io/illustrated-bert/ 而GPT就是基於以上Trasformer架構中的Decoder,作為一種可生成與人類語言相似口吻的深度學習自然語言處理模型。(而BRENT作為Encorder雖然在當時也有重大突破,不過它沒辦法生成文字。)[2] 1. GPT-1 2. GPT-2 3. GPT-3 4. ![](https://hackmd.io/_uploads/H1xRwWIpyT.jpg) 🔺***用AI Image Generator網站***, https://deepai.org/machine-learning-model/text2img 進行文字輸入:「一個主修工程的大三女同學,穿著她漂亮的衣服在圖書館桌前寫文章」的圖片結果。(Dell-E生成圖要錢,這個不用🤪) ## 參考來源: [1] Jayant Chaudhari(2021, Mar 15).*Industrial Revolution From Industry 1.0 to 4.0- A History.* Medium.https://jayantchaudhari.medium.com/industry-1-0-to-4-0-a-history-3f3845d67cec [2]SimonLiu(2023, Feb 7).*淺談 GPT 生成式語言模型(1) — 過去*.Medium.https://blog.infuseai.io/gpt-model-past-introduction-1e2558462e41

    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