李宏毅專題 Track A, B, C 的時間、地點開學前通知

Presentation on theme: "李宏毅專題 Track A, B, C 的時間、地點開學前通知"— Presentation transcript:

1 李宏毅專題 Track A, B, C 的時間、地點開學前通知
深度學習 暑期訓練 (2016) 李宏毅專題 Track A, B, C 的時間、地點開學前通知

2 作業繳交 四個作業 因為是暑假，所以並不強迫繳交 請加入 FB 社團「深度學習暑期訓練 (2016)」
建議修李宏毅專題的同學如果對deep learning 沒有概念 的話一定要做 等一下會講作業大概的內容 都很簡單 作業詳細內容和做法提示預計下周二(8/09)公告在社團上 會使用 keras 這套工具 (歡迎自學 Tensorflow )

3 學習教材 「資料科學愛好者年會」六小時演講錄影 嚴禁外流

4 學習教材 Lecture 1 深度學習簡介 Lecture 2 深度學習技巧 Lecture 3
Convolutional Neural Network (CNN) 和 Recurrent Neural Network (RNN) Lecture 4 深度學習應用與展望 投影片: (可公開)

5 助教 作業一: 盧柏儒 作業二: 黃邦齊 作業三: 李致緯  作業四: 萬家宏  其他助教：莊舜博、鍾佩宏、張瓊之、楊棋宇 作業問題在社團上討論

6 工作站 專題工作站 在週四 (8/04) 中午前以下 google doc 登記 下週二前(8/09)開帳號
如果每組自己有 linux 系統會比較快樂 如果每組自己有 GPU 會更快樂

7 作業說明

8 Machine Learning You said “Hello” Learning ...... “Hi” “How are you”
“Good bye” You write the program for learning. A large amount of audio data

9 Machine Learning This is “cat” Learning ...... “monkey” “cat” “dog”
You write the program for learning. A large amount of images

10 Machine Learning ≈ Looking for a Function
Speech Recognition Image Recognition Playing Go Dialogue System “How are you” “Cat” “5-5” (next move) “Hi” “Hello” (what the user said) (system response)

11 Framework Model Image Recognition: “cat” A set of function “cat”
“money” Repeat again “dot” “snake”

12 Framework Model Supervised Learning Image Recognition: “cat”
A set of function Model Better! Goodness of function f Repeat again Supervised Learning Training Data function input: function output: “monkey” “cat” “dog”

13 Pick the “Best” Function
Image Recognition: Framework “cat” A set of function Neural Network Training Testing Model “cat” Step 1 Goodness of function f Using Pick the “Best” Function Repeat again Step 2 Step 3 Training Data “monkey” “cat” “dog”

14 Deep means many hidden layers
Neural Network neuron Input Layer 1 …… Layer 2 …… Layer L …… Output …… y1 …… y2 …… …… You can connect the neurons by other ways you like  How many layer is deep? CNN just another way to connect the neuros. You can always connect the neurons in your own way. “+” is ignored Each dimension corresponds to a digit (10 dimension is needed) …… yM Input Layer Output Layer Hidden Layers Deep means many hidden layers

15 作業一 教材: lecture 1, lecture 2 Task 1 “5” “0” “4” “1”
basic：higher than a specific accuracy (等助教公布) option：analyze the output of each layer

16 作業一 教材: lecture 1, lecture 2 Task 2 Network 政治 體育 政治 財經
體育 政治 財經 basic：higher than a specific accuracy (等助教公布) option：analyze the output of each layer

17 作業一 教材: lecture 1, lecture 2 More reference:
Example code of task 1: s/mnist_mlp.py Example code of task 2: s/reuters_mlp.py Neural Networks and Deep Learning Chapter 1 - 3

18 作業二 教材: lecture 3 – Convolutional Neural Network Image Recognition
“monkey” “monkey” Network “cat” “cat” “dog” “dog”

19 作業二 教材: lecture 3 – Convolutional Neural Network
Basic：higher than a specific accuracy (等助教公 布) option：analyze the functionality of “filter” More Reference: Example code: s/cifar10_cnn.py Neural Networks and Deep Learning (Chapter 6)

20 作業三 教材: lecture 3 – Recurrent neural network
Machine learns human language Machine writes documents The life is ……. You do not have to teach machine grammars ……. Basic: Let machine generate an English sentence Option: Let machine generate a Chinese sentence

21 作業三 教材: lecture 3 – Recurrent neural network
Machine learns human language More reference Example code: examples/lstm_text_generation.py effectiveness/ Understanding-LSTMs/

22 作業四 教材: lecture 4 Auto-encoder: unsupervised learning NN Encoder code
Basic: visualize the “code”. Does different digits represent by different “code”? NN Decoder code Option: Given a “code”, can machine write a digit?

23 作業四 教材: lecture 4 Auto-encoder: unsupervised learning More reference:
keras.html Advanced: Auto-Encoding Variational Bayes, Generative Adversarial Networks, Replacing “digits” with “images”

24 Have Fun! 