Welcome to the playground of the 6,126,1.00 Machine Learning course offered in the Bachelor of Arts in Business Administration at the University of St. Gallen. The content consists of a series of interactive Jupyter Notebook labs based on Python, IPython Notebook, and PyTorch.
This is currently work in progress so expect minor errors and some rough edges ;)
| Lab | Date | Topic | Binder Launcher(s) | Colab Launcher(s) |
|---|---|---|---|---|
| 00 | Prerequisite | Testing the Lab Environment |  |
 |
| 01 | Prerequisite | Introduction to the Lab Environment | |
|
| 02 | Prerequisite | Fundamentals of Python Programming | |
|
| 03 | April 21st | Traditional Machine Learning I | |
|
| - | April 28th | Traditional Machine Learning II / Self-Coding | Q&A lab | Q&A lab |
| 04 | May 5th | Deep Learning I - ANNs | To be published | To be published |
| 05 | May 12th | Deep Learning II - CNNs | To be published | To be published |
| - | May 19th | Self-Coding | Q&A lab | Q&A lab |
| - | May 26th | Coding Challenge - Submission Deadline | No lab | No lab |
| Lab | Topic | Binder Launchers | Colab Launchers |
|---|---|---|---|
| 06 | Residual Neural Network (ResNet) Classification | To be published | To be published |
Install dependencies via pip install -r requirements.txt.
You can run the lab Notebooks in the cloud using either binder or Google Colab, or locally on your computer.
This is the easiest way to run a Notebook in your web browser: just click on the binder badge next to the Notebooks below and off you go. Binder is a service that lets you run Jupyter Notebooks in their cloud at no charge. There is no registration and no login required. However, keep in mind that you cannot save any data or your Notebook file in the cloud (you can save them on your computer, though). Also, starting a binder Notebook can take quite some time, but the performance during runtime is good. For more information, please refer to the Binder documentation.
Similar to binder, you just have to click the Colab badge next to the Notebooks below. All you need is a Google login (e.g., your login information for gmail) and you can use this service at no charge. Two advantages of Colab are that (1) you can save your Notebooks directly into your Google Drive and read data from there, and (2) Google provides you with some limited GPU capabilities free of charge (this will be an interesting feature for the coding challenge). This last feature will save you time by making the training of deep artificial neural networks much faster.
If you prefer to run Notebooks locally on your computer, you will need to install Python. If you choose to do so, we recommend to install Anaconda Python, a package that combines the latest version of Python with the most common supplemental modules for data science and machine learning, as well as a Jupyter Notebook server that runs on your computer locally. Check out our Python and Jupyter Notebook installation guide below for a step-by-step manual.
To run our Notebooks locally, you can download them individually from this website, or simply clone this repository to your computer.
If you need help running Python and/or Jupyter Notebooks, please don't hesitate to contact us (see below)!
Python and Jupyter Notebook Installation:
Cloning the repository to Azure Notebooks:
Pls. don't hesitate to send us all your questions using the course mail address:
