mldds-courseware

Machine Learning-driven Data Science

Slides and Workshop material (under development) for the Machine Learning classes from NUS ISS Stackup.

• Setup
• Module Index

Setting up your machine

Windows Setup

MacOS Setup

Slides

Slides are now on Google Drive

Module index

The index contains links to HTML renderings of the Jupyter notebooks for browsing convenience.

To run the workshop exercises, you can clone this repository.

• 1 Getting Started
  • 1.1 Introduction [html, ipynb]
  • 1.2 NumPy [html, ipynb]
  • 1.2.1 NumPy Tensor Slicing [html, ipynb]
  • 1.3 Pandas [html, ipynb]
  • 1.4 Matplotlib [html, ipynb]
  • 1.5 My First Model [html, ipynb]
• 2 Basic Machine Learning Algorithms
  • 2.1 Training Basics [html, ipynb]
  • 2.1.2 Gradient Descent Notes [html, ipynb]
  • 2.2 Linear Regression [html, ipynb]
  • 2.2 Classification [html, ipynb]
  • 2.3 Clustering [html, ipynb]
  • 2.4 Decision Trees [html, ipynb]
  • 2.5 Dimensionality Reduction [html, ipynb]
• 3 Image Recognition and Text Processing
  • 3.1 Neural Networks [html, ipynb]
  • 3.2 Image Recognition [html, ipynb]
  • 3.3 Transfer Learning [html, ipynb]
  • 3.4 Adversarial Learning [html, ipynb]
  • 3.5 Text Processing [html, ipynb]
  • 3.6 Word Vectors [html, ipynb]
• 4 Recurrent Networks, Time Series Forecasting and Speech Recognition
  • 4.1 Time Series Forecasting [html, ipynb]
  • 4.2 Speech Recognition [html, ipynb]
• 5 Deployment
  • 5.1 Deploying an Scikit-learn model [train, deploy]
  • 5.2 Deploying a Keras model [train, deploy]
• 6 Project
  • 6.1 Template [html, ipynb]

StackUp | Institute of Systems Science | National University of Singapore

This site is open source. Improve this page.