清華大學應數系
演算法
Algorithms
Robotic AI Lab
Applied Math, National Tsing Hua University
劉晉良
Jinn-Liang Liu

 

 

2019 Spring Course

演算法 Algorithms

南大校區9307, 1:20 – 2:50 – 4:10pm, Mondays (2019.2.22 – 2019.6.10)

Reports: Do Proj1 and a project of your choice and Send reports in ppt (Demo) to jinnliu@mail.nd.nthu.edu.tw (email 標題:姓名 學號  Report 1, 2, or 3)  by Mondays 3/25; 4/29; 6/10.

 

工業革命:動力1.0 (1760),電力2.0 (1870),數位3.0 (1945),智力4.0 (2016 AlphaGo)

AI 聽說讀寫食衣住育樂金…, ABC.

 

l   AI abc: An Introduction to Machine Learning

l   Gradient Descent and Backpropagation in Machine Learning (Automatic Differentiation: Forward & Reverse Modes, Jacobian)

l   Convolution in Machine Learning (Convolution)

 

Part I   Computer Programming (Browse and Use) GitHub

1.        Python Programming

2.       TensorFlow, TensorBoard (YouTube1),
Colab: 1.
Style Transfer (YouTube2, Code2), 2. Time Series (YouTube3), 3. YOLO (YouTube4, Code3), 4. Stock (YouTube5, Code4), 5. Game (OpenAI RL Code5)

(Proj1: A. Colab, tf3-MNIST.py, keras_tensorboard.ipynb (Tutorial))

3.        PyTorch (PyTorch Autograd, PyTorch入門, MNIST.ipynb, MNIST.py)

4.        C++ Programming

 

A.   Cloud Computing by Colab: Google Chrome => Google Account => Google 雲端硬碟 => Click tf1.ipynb => Upload tf1.ipynb to Google 雲端硬碟 => Click on tf1.ipynb => Install Colab Notebooks => Run tf1.ipynb (Done!)

B.    Local Computing by jupyter: Install Anaconda3-4.2.0 (or more Anaconda) => Anaconda Navigator => Environments => Install TensorFlow  => Home => Launch jupyter => jupyter => Files on 筆電 => Click on tf1.ipynb => Run tf1.ipynb (Done!)
How to run py code on jupyter: tf1.py =>  Creat a new file tf1.ipynb with only one line “import tf1” => Run the cell of “import tf1” (Done!)

C.    Install PyTorch via Anaconda: Click Anaconda Prompt => >conda install PyTorch -c PyTorch  => (take a while) => >pip install torchvision => Try 1. import numpy as np  2. import torch  3. x = torch.empty(5, 3)  4. print(x)  on jupyter (Done!)

D.   Local Computing by PyCharm:

1. tf1.py: # Put this file tf1.py in D:\AI\TF (in English, no Chinese). 
# Install Anaconda3-4.2.0 => Install PyCharm Community Edition 2017.1.5 for Windows 
=> PyCharm => Create New Project => Location: D:\AI\TF 
=> Interpreter: Click on Create Conda Env (Far Right Button) 
=> Click Create => Click File => Open tf1.py => Tools 
=> Python Console => >>>  import pip => >>> pip.main(['install', 'tensorflow'])  
=> Wait for  >>>  => Click the green triangle button (Run tf1). Done!
# See YouTube Link for more if needed.
2. tf2.py: # How to use TensorBoard. # PyCharm => View => Tool Windows 
=> Terminal => Click the green + sign in the Terminal Screen 
=> (C:\Users\Jinn\Anaconda3\envs\untitled1) D:\AI\TF> tensorboard --logdir="./graphs" --port 6006 
=> Copy http://Jinn-PC:6006 => Google  Chrome  
=> Paste http://Jinn-PC:6006 to Chrome's http address  
=> GRAPHS (the graph of a, b, Add)
3. TF mnist 1.0 (tf3-MNIST.py) => # Google Chrome => http://Jinn-PC:6006 => GRAPHS => # Error: matplotlib not installed 
=> # PyCharm => File => Setting => Project: TF => Project Interpreter => + => matplotlib 

=> Specify version => Install # Save  zout_MNIST_1.0.png

 

Part II   Supervised Learning (Read and Work)

1.        A Simple Learning Model: Classification, Target, Hypothesis, Training Data, Learning Algorithm, Weights, Bias, Supervised and Unsupervised Learning

2.        Google Tutorial for ML Beginners: Image Recognition, MNIST, Softmax Regression (92%), Cross Entropy, Gradient Descent, Back Propagation, Computation Graph (TF mnist 1.0)

3.        Tensorflow and Deep Learning I (by Martin Gorner) : Deep Learning Network, ReLU, Learning Rate (98%), Overfitting, Dropout (98.2%), Convolutional Neural Network (99.3%)  (TF mnist 3.1)

4.        Tensorflow and Deep Learning II (by Martin Gorner)  (RNN1): Batch Normalization (99.5%) (TF mnist 4.2), Data Whitening, Fully Connected Network, TensorFlow API, MNIST Record (Kaggle: 100%), Recurrent Neural Network, Deep RNN, Long Short Term Memory, Gated Recurrent Unit, Language Model

 

Part III   Theories of Deep Learning

1.        Lectures at MIT (Book: Deep Learning by Goodfellow, Bengio, Courville)

2.        Lectures at Chicago

3.        Lectures at Stanford