# Introduction **[ML網站](http://speech.ee.ntu.edu.tw/~tlkagk/courses_ML20.html)** 特點 --- 機器學習就是自動找函式 課程地圖 --- :::info **Regression** - 函式輸出是一個數值(scalar) ::: :::info **Classifcation** - Binary Classifcation - RNN - 輸出只有兩個可能Yes or No(pos or neg) - Multi-class Classifcation - CNN - 準備好N個選項,讓機器去選擇 ::: :::info **Generation** 產生有結構的複雜東西 - Seq2seq - ex : 翻譯,產生文句 - GAN - ex : 圖片生成 ::: :::info **Unsupervised Learning** 給機器一堆Data,但沒有標註 - Unsupervised Learning - GAN ::: :::info **Reinforcement Learning** 讓機器跟自己或跟別人對戰訓練,機器自己要找出策略 - Reinforcement Learning ::: :::success **Explainable AI** - 解釋得出答案的理由 ::: :::success **Adversarial Attack** - 惡意攻擊、惡意雜訊造成機器崩壞 ::: :::success **Network Compression** - 把碩大的network縮小 ::: :::success **Anomaly Dection** - 當input為機器無法辨識的東西,它是否能知道它自己不知道 ::: :::success **Transfer Learning(Domain Adversarial Learing)** - 當訓練資料與測試資料不一樣時,有沒有辦法讓機器能學到一些東西 ::: :::success **Mata Learing** - 學習如何學習 - 機器自己學習自己的學習演算法 ::: :::success **Life-long Learning** - 機器的終身學習 ::: Learning Type --- - **Supervised Learning** (給機器一個input,並標註它的正確理想output) - Regression - Classificaton - RNN - CNN - Seq2seq - **Unsupervised Learning** (給機器一堆Data,但沒有標註) - Unsupervised Learning - GAN - **Reinforcement Learning** (讓機器跟自己或跟別人對戰訓練,機器自己要找出策略) - Reinforcement Learning ---  ###### tags: `ML2020`
×
Sign in
Email
Password
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