Skip to content

A series of interactive labs we prepared for the Introduction into Machine Learning and Deep Learning course. The content of the series is based on Python, IPython Notebook, and PyTorch.

GitiHubi/courseMLDL

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MUG Master Course :: "Introduction into Machine Learning and Deep Learning"

A series of interactive lab notebooks we prepared for the 7.253.1,00 Introduction into Machine Learning and Deep Learning course offered in the Master of Arts in Business Management (MUG) at the University of St.Gallen (HSG).

The content is build on a series of Jupyter Notebooks based on Python, IPython Notebook, Scikit-Learn and PyTorch.

License: GPL v3

Course Banner

A series of interactive lab notebooks we prepared for the Introduction into Machine Learning and Deep Learning course. The content of the series is based on Python, IPython Notebook, and PyTorch.

Cloning the repository to Azure Notebooks: Azure Notebooks

This is currently work in progress so expect minor errors and some rough edges ;)

Running the Lab Notebooks

Lab 00: "Testing the Lab Environment" (Binder, Open In Colab)

Lab 01: "Introduction to the Lab Environment" (Binder, Open In Colab)

Lab 02: "Fundamentals of Python Programming" Open In Colab

Lab 03: "Supervised Machine Learning"

  • Naive-Bayes: (Binder, Open In Colab)
  • k-Nearest Neighbors: (Binder, Open In Colab)
  • Logistic Regression: (Binder, Open In Colab)

Lab 04: "Unsupervised Machine Learning"

  • k-Means Clustering: (Binder, Open In Colab)
  • Expectation-Maximization: (Binder, Open In Colab)

Lab 05: "Supervised Deep Learning - ANNs" (Binder, Open In Colab)

Lab 06: "Supervised Deep Learning - CNNs" (Binder, Open In Colab)

Getting Started

Install dependencies via pip install -r requirements.txt.

Questions?

About

A series of interactive labs we prepared for the Introduction into Machine Learning and Deep Learning course. The content of the series is based on Python, IPython Notebook, and PyTorch.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published