Skip to content

Let's explore machine-learning together. A collection of in-depth articles that explain various aspects of ML.

Notifications You must be signed in to change notification settings

wmeints/machinelearning-with-willem

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 

Repository files navigation

This repository contains all the parts to my series "Machine Learning with Willem". Consider this repository a self-paced workshop where we explore machine-learning in any order you like.

Goal for this repository

  • Teach you various machine learning projects

  • Have fun while writing down some of my practices

  • Provide an open source knowledge base on how to build machine-learning projects

System requirements

All the samples run on WSL2. I’ve tried various scenarios over the years to get things working on Windows. It just doesn’t work that well on Windows when compared to how smooth things work on WSL2 and plain Linux.

Please make sure you have the following tools on your machine when exploring the topics in this repository:

  1. Visual Studio Code or some other editor with language server support

  2. Python 3.12 or higher

  3. 16 GB of Memory and a decent CPU

  4. WSL2 with Ubuntu 22.04

For the deep learning topics I recommend a good graphics card that supports [Cuda](https://developer.nvidia.com/cuda-toolkit) with 8 GB of memory.

Getting started

Before you dive into the different topics, please make sure you’ve followed the basic tutorials! I’ve created the following tutorials to help you get started:

  1. Installing WSL2 on Windows 11

  2. Installing Python 3.12 on Ubuntu 22.04

  3. Setting up a basic Python project with Poetry and virtualenv

After completing the tutorials you know enough of the basics to explore all the other topics in this repository.

Structure of this repository

I’ve split the repository in the following parts:

  1. MLOps

  2. Supervised learning

  3. Unsupervised learning

  4. Time-series processing

  5. Deep learning

  6. Generative AI applications

  7. Fairness, and safety

  8. Interpretability and explainability

Some sections will be split into subsections as I see fit. These are pretty big topics, and I think it makes sense to split them into useful subsections that you can explore separately. There’s no predefined order of importance in the topics. For me, they’re all the same.

At some point I’ll reorganize the repository so the order makes more sense. Since it’s all incomplete, I’m not going to bother myself ordering things that don’t have an order yet.

Frequently asked questions

Q: How often will you provide updates? A: Once per week, on Saturday usually

Q: Is there an order in which I should go through the topics? A: Not really, consider this a practical reference to things I’ve learned over the years

Q: I’m missing a topic, can I propose one? A: Yes, you can. Please submit an issue

Q: Do you have samples? A: Each of the topics contains a sample. It simply wouldn’t be fun without.

About

Let's explore machine-learning together. A collection of in-depth articles that explain various aspects of ML.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published