mint-lab/dl_tutorial: Machine Learning and Deep Learning Tutorial · GitHub

Machine Learning and Deep learning Tutorial (shortly ML/DL Tutorial) has been initiated to teach undergraduate students in SEOULTECH about basic concepts of machine learning and deep learning with hands-on practices using scikit-learn and PyTorch. Even though there are so many good lectures and tutorials on machine learning and deep learning, I would like to share my viewpoint and summary with humble slides and examples because I also have learned many things from open and public lectures, tutorials, and articles. I hope that my slides and examples are also helpful to others.

• To clone this repository (codes and slides): git clone https://github.com/mint-lab/dl_tutorial.git
• To fork this repository to your Github: Click here
• To download codes and slides as a ZIP file: Click here

This tutorial is the last part of my lecture. Its prior knowledge on Python and mathematics is also available in Programming Meets Mathematics.

• Machine Learning with scikit-learn
• Deep Learning with PyTorch

📝 Source codes are enumerated in the order of its lecture slides.

• scikit-learn
  • Three Steps of scikit-learn: Instantiation, fit and predict
• Classification
  • SVM Classifiers
  • Decision Tree Classifiers
  • Naive Bayes Classifiers
  • More Classifiers
  • Lab) Breast Cancer Classification [slides] [skeleton code]
• Regression
  • Linear Regression
  • SVM Regressors
• Clustering
  • K-means Clustering
• Data Separation
  • Lab) Breast Cancer Classification with Cross-validation [slides] [skeleton code]

📝 Source codes are enumerated in the order of its lecture slides.

• PyTorch
  • Creating a Tensor
  • Reshaping a Tensor
  • Line Fitting from Two Points
  • CPU vs. GPU-acceleration
  • Automatic Differentiation
  • Automatic Differentiation - More Analysis
  • Gradient Descent by Hands
  • Gradient Descent by torch.optim
  • Lab) Object Detection using YOLO [slides] [skeleton code (py)] [skeleton code (ipynb)]
• Neural Network
  • Visualizing Activation Functions
  • Observing Vanishing Gradient - Sigmoid
  • Observing Vanishing Gradient - ReLU
  • The Iris Flower Dataset [UCI ML Repository]
    • Iris Flower Classification - No Class
    • Iris Flower Classification - My Style
• Convolutional Neural Network
  • The MNIST Dataset [homepage]
    • Loading the MNIST Dataset
    • Digit Classificaiton with the MNIST Dataset
    • Loading My Network and Testing It
    • Different Styles for NN Classes
  • Visualizing Learning Rate Schedulers
• Recurrent Neural Network
  • The Name2Lang Dataset [homepage]
    • Name2Lang Classification with a Character-level RNN

Note) All examples contain their basic NN architectures and hyperparameters. One of main objectives in practices will be their performance improvement by changing the architectures and selecting hyperparameters.

• Beerware

• Sunglok Choi