Code, exercises and tutorials of my personal blog !

Machine Learning Tutorials and Articles

In this repository, I’m uploading code, notebooks and articles from my personal blog : https://maelfabien.github.io/. Don’t hesitate to ⭐ the repo if you enjoy my work ! New articles are being published weekly !

🚀 I recently started a newsletter in which I gather some cool articles I wrote on a topic, interesting Github repositories, projects, papers and more! I’ll try to send 1 to 2 emails per month. If you want to stay in the loop, just click here : http://eepurl.com/gyYzi5

NEW: I’m looking for motivated Data Scientists to help me build high environmental impact algorithms (CV essentially). Please contact me if you’re interested (from my website, contact section)

Table of Content :

• CheatSheets
• Latest Articles
• Machine Learning
• Deep Learning
• Data Engineering
• Written for other blogs
• Medium Articles

First of all, if you’re not familiar with the key concepts of machine learrning, make sure to check this first article : https://maelfabien.github.io/machinelearning/ml_base/

The repository is organized the following way :

• articles and tutorials are posted by category
• there is a link to the article in question with the read time specified
• the is a link to the code folder for each article

You would like to work on an article with me ? Or you would like me to work on a specific topic ? Feel free to reach out ! (mael.fabien@gmail.com)

Machine Learning Cheatsheet :

For the moment, these cheat sheets are written manually. I’d like to create a visual content later that would both dive in the maths and illustrate clearly each algorithm.

1. Supervised Learning

2. Unsupervised Learning

Projects

I have made a series of projects, all of which are available on my blog : https://maelfabien.github.io/portfolio/#

Latest articles

SP - Voice Gender Detection web application: How to extract relevant features and build a voice gender detection application using MFCC, GMMs and a provided dataset.

SP - Sound Visualization (3/3): Dive into spectrograms, chromagrams, tempograms, spectral power density and more…

SP - Sound Feature Extraction (2/3): An overview with a Python implementation of the different sound features to extract.

SP - Introduction to Voice Processing in Python (1/3): Summary of the book “Voice Computing with Python” with concepts, code and examples.

SP - Building a Voice Activity Detection web application : Voice detection can be used to start a voice assistant or in emergency cases for example. Here’s how to implement it using simple methods.

CV - Implementing YoloV3 for Object Detection : Learn how to implement YoloV3 and detect objects on your images and videos.

NLP - Easy Question Answering with AllenNLP : Understand the core concepts and create a simple example of Question Answering.

NLP - Data Augmentation in NLP : Details of the implementation of “Easy Data Augmentation” paper.

NLP - Character-level LSTMs to predict gender of first names : 90% accuracy on predictiong the gender of French and US first names.

NLP - Few Shot Text Classification : Implementation of a simple paper that leverages pre-trained models for few shot text classification.

NLP - Improved Few Shot Text Classification : Improving previous results with Data Augmentation and more complex models.

RL - Introduction to Reinforcement Learning : An introduction to the basic building blocks of reinforcement learning.

RL - Markov Decision Process : Overview of Markov Decision Process and Bellman Equation.

RL - Planning by Dynamic Programming : Introduction to Dynamic Programming, including Policy and Value Iteration.

NLP - I trained a Neural Network to speak like me : Having written over 100 articles, I trained a NN to write articles just like me.

DL - How do Neural Networks learn? : Dive into feedforward process and back-propagation.

Two general articles :

1. Understanding Computer Components (6mn read) https://maelfabien.github.io/bigdata/comp_components/

2. Useful Bash commands (1mn read) https://maelfabien.github.io/bigdata/Terminal/

3. Making your code production ready (1mn read) https://maelfabien.github.io/bigdata/Code/

Written for other blogs

1. Who’s the painter? - For explorium.ai : An illustration of how data enrichment and feature engineering can improve a model.

2. Machine Learning Interpretability and Explainability (1/2) - For explorium.ai : An introduction to interpretable models with code and examples.

3. Machine Learning Interpretability and Explainability (2/2) - For explorium.ai : An introduction to explainability in Machine Learning with code and examples.

4. A guide to Face Detection - For digitalminds.io : An overview of the different techniques face Face Detection in Python (with code).

5. Modéliser des distributions avec Python (French) - For Stat4Decision: Distribution fitting web application with Streamlit.

6. Introduction au Traitement Automatique de Language Naturel (TAL) (French) - For Stat4Decision

Medium Articles

1. Boosting and Adaboost clearly explained : https://towardsdatascience.com/boosting-and-adaboost-clearly-explained-856e21152d3e

2. A guide to Face Detection in Python: https://towardsdatascience.com/a-guide-to-face-detection-in-python-3eab0f6b9fc1

3. Markov Chains and HMMs: https://towardsdatascience.com/markov-chains-and-hmms-ceaf2c854788

4. Introduction to Graphs (Part 1): https://towardsdatascience.com/introduction-to-graphs-part-1-2de6cda8c5a5

5. Graph Algorithms (Part 2): https://towardsdatascience.com/graph-algorithms-part-2-dce0b2734a1d

6. Graph Algorithms (Part 3): https://towardsdatascience.com/learning-in-graphs-with-python-part-3-8d5513eef62d

7. I trained a neural network to speak like me: https://towardsdatascience.com/i-trained-a-network-to-speak-like-me-9552c16e2396

Stay tuned :)