Kevin Kao
    • 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 New
    • Engagement control
    • Make a copy
    • 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 Note Insights Versions and GitHub Sync Sharing URL Create Help
Create Create new note Create a note from template
Menu
Options
Engagement control Make a copy 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
    • Any changes
      Be notified of any changes
    • Mention me
      Be notified of mention me
    • Unsubscribe
    # 人工智慧 僑光科技大學 資訊科技系 2021/02/25 ~ 2021/06/24 授課老師:高吉隆 電子信箱:[kevinkao888@gmail.com](mailto://kevinkao888@gmail.com) ###### tags: `講義` --- # 課程介紹 * 課程大綱 * 每週目標 * 成績計算 ---- ## 課程大綱 1. 人工智慧的基礎知識 2. 機器學習的基礎知識 3. 機器學習的核心技術 4. 機器學習的演算法 5. 深度學習的基礎知識 6. 深度學習的核心技術 7. 深度學習的演算法 8. 開發環境與系統開發 ---- ## 每週目標 * 前 9 週上課目標 * 案例研讀 * 作業繳交 * 案例報告 * 後 9 週上課目標 * 分組實作 * 規劃報告 ---- |週| 前 9 週上課目標 | |:-:| --------------- | | 1 | 資訊創新之概念 | | 2 | 競賽案例分享(一) | | 3 | 案例閱讀題目選定 | | 4 | 報告初稿繳交 | | 5 | 案例分享報告(9組) | | 6 | 案例分享報告(9組) | | 7 | 案例分享報告(9組) | | 8 | 案例分享報告(9組) | | 9 | 案例分享報告(9組) | ---- | 週 | 後 9 週上課目標 | |:--:| --------------- | | 10 | 分組與題目訂定 | | 11 | 分組討論與分析| | 12 | 分組討論 | | 13 | 書面資料製作 | | 14 | 書面資料繳交 | | 15 | 影片介紹製作 | | 16 | 分組成果報告(9組) | | 17 | 分組成果報告(9組) | | 18 | 分組成果報告(9組) | ---- ## 評分標準 * 平時成績:50% * 上課互動:10% * 證照考:20% * 讀書報告:20% * 期中成績:20% * 期中考試:20% * 期末成績:30% * 期末報告:30% --- ### 第一次小考成績統計(107孝) ||平均|最高|最低|未到考|不及格 |:-:|-:|-:|-:|-:|-:| |原始分數|90|99|75|10人|0人 |含未到考|87|99|70|70|0人 ![](https://i.imgur.com/5Dp1efK.png) ---- ### 期中考成績統計(107孝) ||平均|最高|最低|未到考|不及格 |:-:|-:|-:|-:|-:|-:| |原始分數|70|95|38|3人|10人 |加5分後|73|100|40|40|11人 ![](https://i.imgur.com/Td5Qy1N.png) --- ### 讀書報告 * 參考書:向AI贏家學習 1. 「AI食品原料檢查設備」,逆轉思維確保食安 2. 「包裝設計喜好度評估預測AI服務系統」,徹底改變市調作業 3. 從水處理到巧克力,流體動態影片與靜態影像辨識大不同 4. 自動辨識貨架商品建議配置,改變製造商、批發、零售的角力 5. 從改善生產流程到改善製造業,提升人工目測檢查效率 6. 用深度學習掌握超商香菸陳列,以競賽作為獲得新技術的工具 7. 分析餐廳暢銷菜單,開發外食數據標註技術 8. 數據化強化選手戰力、分析球隊效益,訓練強度定量化 9. AI即時自動模糊加工處理,5G時代不只是通訊的多樣化服務 10. 從日常對話到跨國商務,運用深度學習自動翻譯降低語言門檻 11. 連結現實與數位,找便宜加油站、停車空位輕鬆搞定 12. 「AI股票投資組合診斷」協助投資,讓資產變十三倍 13. 重現熟練操作員的雙眼,提高五倍垃圾處理效率 14. 自動排除幼兒「NG照片」,解決幼兒園照護課題 15. 餐廳自動結帳系統因應人力不足問題,讓氣氛更輕鬆活絡 16. 辨識貨車車牌影像,縮短物流據點等候貨物時間 17. 讀取財務報表數字自動製作報告書,實現高準確率自動化智庫 18. 偵測駕駛習慣和風險因子,以資訊科技減少交通事故 19. AI與機器的「拉鋸戰」,食品加工製造生產線另闢蹊徑的智慧 20. 自動讀取加工設計圖面,解決產業嚴重人力不足問題 21. 以原有強項為基礎,建立低單價累積長程獲利的商業模式 22. 運用深度學習新手法更精確預測降雨,不用超級電腦即可完成 23. 全球首創運用深度學習偵測證交所不當交易,假買賣無所遁形 24. 用AI揭發網路名人不法行為,揪出灌水的網紅追蹤者人數 25. 從眼底影像解讀健康狀況,設備的資料加工化為商機 26. 超低價深度學習系統,運用邊緣裝置實現高準確率人臉認證 ---- ### 人工智慧期中心得報告 * 請找1-2位同學成為1小組 * 填寫主題名稱、組長及組員名單 * 填寫網址:[連結](https://hackmd.io/A-NoYbEHQbCIcUiSIPhKpw?edit) * 繳交:免口頭報告,上傳影片至平台 * 內容:3分鐘影片(需結合簡報、錄音等內容) * 可用[Powtoon](https://www.powtoon.com/index/)來製作動態影片 * 可用[oCam](http://wis.ocu.edu.tw/base/10001/board/1000022673/000000044/WM60a47e5e1d4d5.exe)製作螢幕錄製及錄音 * 可用[MP4Tools](http://wis.ocu.edu.tw/base/10001/board/1000022673/000000044/WM5e74663c3230d.exe)來影片的切割、合併 * 請於規定時間內上傳作業至僑光網路教學平台 * 上傳網址:[連結](http://wis.ocu.edu.tw/) ---- ### 人工智慧期末報告 * 請找1-3位同學成為1小組 * 填寫主題名稱、組長及組員名單 * 填寫網址:[連結](https://hackmd.io/N2_k5IWoSG2U-GgLzf9Ykg?edit) * 內容:以下二個方案擇一(3分鐘影片) * 方案一:請直接使用汽車價格預測報告 * 使用該模型但資料不能是汽車價格 * 可以找其他資料(不是汽車的資料) * 方案二:請使用在MLS中其他案例 * 請同學填寫期末報告主題名稱 * 繳交:上傳影片至[僑光網路教學平台](http://wis.ocu.edu.tw/) --- ### Microsoft Machine Learning Studio * 網址:[Machine Learning Studio](https://azure.microsoft.com/zh-tw/services/machine-learning-studio/) ![](https://i.imgur.com/WHMWBZc.png =700x500) ---- #### Machine Learning Stduio 特色 * 不需要寫程式即可完成機器學習的完整過程 * 包含資料整理、模型設計、訓練、測試和佈署 * 不必申請雲端AZure帳號,在雲端上使用 * 若需上傳資料,需申請Microsoft免費帳號 * 平台包含許多範例資料,可透過案例學習 * 可透過相同界面,上傳資料做案例研究 * 可載入預先訓練好之模型,以簡短步驟完成模型 * 只要會調整模型數據,即可直接訓練 * 整個機器學習過程只要5分鐘即可完成 * 方便初學者及跨領域之專業人員使用 ---- #### Machine Learning Studio 示範 * 網址:[https://studio.azureml.net/](https://studio.azureml.net/) * 三種方案使用 ![](https://i.imgur.com/kJHOOWp.png) ---- #### AZure ML Studio 三種方案 * 快速測試:Guest Workspace * 每次8小時測試(永久),免登入帳號 * 快速使用現成範例資料及所有模型 * 普遍使用:Free Workspace * 註冊微軟帳號、10G空間、免費使用 * 可以用 GMail 帳號申請,但不能用 OCU * 也可以用手機號碼申請,再申請 outlook 帳號 * 企業應用:Standard Workspace * 完整服務等級支援 * 可直接捉取AZure雲端空間 ---- #### Machine Learning 基礎知識資源 * Youtube影片:台大資工教授林軒田提供 * [連結](https://youtu.be/nQvpFSMPhr0) * 微軟教學網頁:[連結](https://docs.microsoft.com/zh-tw/azure/machine-learning/classic/studio-classic-overview) ---- ### ML Studio 案例操作 汽車價格預測 * 使用 Guest Workspace:[連結](https://studio.azureml.net/Home/Anonymous)、[說明文件](https://docs.microsoft.com/zh-tw/azure/machine-learning/studio/create-experiment) * 左下角:New->Blank Experiment->輸入標題 * 輸入:Automobile price data->拖曳 * 資料來源:[連結](https://archive.ics.uci.edu/ml/machine-learning-databases/autos/imports-85.data) * 資料說明:[連結](https://archive.ics.uci.edu/ml/machine-learning-databases/autos/imports-85.names) * Dataset->Visualize->用統計圖形了解屬性 * 統計資訊: * Feature Type:String / Numeric * String Statistics:Unique / Missing Values * Numberic Statistics:Mean / Median / Min / Max / Standard Deviation ---- #### ML Studio 案例操作 汽車價格預測(2) * 輸入:Select Columns in Dataset() -> 拖曳 * 拉線從:Automobile price data(Row) * 點按:Lanuch column selector -> WITH RULES * 選擇:Begin With -> ALL COLUMNS -> exclude -> normalized-losses * 點按:RUN -> 26 Columns -> 25 Columns * 搜尋區輸入:Clean Missing Data -> 拖曳 * 拉線從:Select Columns in Dataset * 點按:Lanuch column selector -> WITH RULES * 設定:Cleaning mode -> Remove entire row * 點按:RUN -> 205 Rows -> 193 Rows ---- #### ML Studio 案例操作 汽車價格預測(3) * 搜尋區輸入:Select Columns in Dataset -> 拖曳 * 拉線從:Clean Missing Data * 點按:Lanuch column selector -> BY NAMES * 選擇:make,body-style,wheel-base,engine-size,horsepower,peak-rpm,highway-mpg,price * 搜尋區輸入:Split Data -> 拖曳 * 拉線從:Select Columns in Dataset * 輸入:Fraction of rows in the first output dataset (0.75) * 輸入:Random seed (12345) * 點按:RUN -> 193 Rows -> 145 and 48 Rows ---- #### ML Studio 案例操作 汽車價格預測(4) * 搜尋區輸入:Linear Regression -> 拖曳 * 搜尋區輸入:Train Model -> 拖曳 * 拉線從:Linear Regression * 拉線從:Split Data(左邊) * 點按:Lanuch column selector -> WITH RULES * 選擇:price * 搜尋區輸入:Score Model -> 拖曳 * 拉線從:Train Model * 拉線從:Score Model * 搜尋區輸入:Evaluate Model -> 拖曳 * 拉線從:Score Model ---- #### ML Studio 案例操作 汽車價格預測(5) ![](https://i.imgur.com/31XKEPx.png =600x600) ---- #### ML Studio 案例操作 汽車價格預測(6) ![](https://i.imgur.com/3sAJ96e.png =800x600) ---- #### ML Studio 案例操作 汽車價格預測(6) * 價格與預測值之比較 ![](https://i.imgur.com/hsfZlCX.png) --- ### ML Studio 案例操作 英文字母識別 * 使用 Guest Workspace:[連結](https://studio.azureml.net/Home/Anonymous) * 左下角:New -> Search experiment templates * 輸入 Sample 7:找到 Letter Recognition * Train, Test, Evaluate for Multiclass Classification * 選擇 View in Gallery:範例說明([連結](https://gallery.azure.ai/Experiment/a635502fc98b402a890efe21cec65b92)) * 選擇 Open in Studio:實作練習([連結](https://studio.azureml.net/Home/ViewWorkspaceCached/1309654da1e445e0a944df88dfdef58e#Workspaces/Experiments/Experiment/1309654da1e445e0a944df88dfdef58e.f-id.1c9effcb89fc44af98ce01f0f38bb380/ViewExperiment)) ---- #### ML Studio 案例操作 英文字母識別(2) * 資料集介紹:[下載](http://archive.ics.uci.edu/ml/machine-learning-databases/letter-recognition/) * 20000筆: * 採集來源:20種不同字體 * 處理方式:隨機扭曲變形後計算各個特徵值 * 標準化:將特徵值數值轉換至數字範圍(0-15) * 17欄: * 1㯗:大寫字母(A-Z) * 16欄:數字特徵值(整數)(0-15) ---- #### ML Studio 案例操作 英文字母識別(3) * 各種特徵值計算方式(如以下幾種) * y-box:vertical position of box * width:width of box * high:height of box * onpix:total # on pixels * x-bar:mean x of on pixels in box * y-bar:mean y of on pixels in box * x2bar:mean x variance ---- #### ML Studio 案例操作 英文字母識別(4) * 各種特徵值計算方式(如以下幾種) * y2bar:mean y variance * xybar:mean x y correlation * x2ybr:mean of x * x * y * xy2br:mean of x * y * y * x-ege:mean edge count left to right * xegvy:correlation of x-ege with y) * y-ege:mean edge count bottom to top * yegvx:correlation of y-ege with x ---- #### ML Studio 案例操作 英文字母識別(5) * 機器學習模型 ![](https://i.imgur.com/oHAvqsx.png =550x550) ---- #### ML Studio 案例操作 英文字母識別(6) * 資料來源統計 ![](https://i.imgur.com/c6WBMVO.png) ---- #### ML Studio 案例操作 英文字母識別(7) * 資料切割:部分訓練、部分測試 ![](https://i.imgur.com/6JLiSje.png) ---- #### ML Studio 案例操作 英文字母識別(8) * 預測分數: ![](https://i.imgur.com/XRJsrEQ.png)

    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