Thanks to visit codestin.com
Credit goes to github.com

Skip to content
View MarouaneAEF's full-sized avatar
:octocat:
:octocat:
1 follower · 3 following

Achievements

Achievement: Quickdraw

Achievements

Achievement: Quickdraw

Block or report MarouaneAEF

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
MarouaneAEF/README.md

Bannière Marouane Ait El Faqir

Bonjour 👋

🎓 Machine Learning Engineer with a strong scientific background.
I design intelligent solutions at the crossroads of R&D and production.
Passionate about probabilistic models, deep learning, and optimization,
I build robust architectures for:

  • 🔍 Anomaly detection
  • 🎨 Generative modeling
  • 🧩 Unsupervised learning

🎯 Current Focus

Mastering MLOps tools to scale ML systems efficiently.

💼 What I Do

🔍 Probabilistic Modeling & Anomaly Detection

  • GMM-VAE: Variational Autoencoder with GMM clustering for unsupervised anomaly detection
  • BiGAN-based Anomaly Detector: Detection using Bidirectional GANs
  • Expectation-Maximization: Custom implementation of the EM algorithm

🧠 Applied Research

  • Neural-E-M: Hybrid algorithm combining neural networks and EM
  • L1BSR: Image reconstruction using L1 regularization

📈 MLOps / Production-Grade ML (in progress)

  • Model tracking with MLflow
  • Deployment on AWS using SageMaker
  • Unit testing, CI/CD, and containerization

🌐 My Ecosystem

  • 🧠 PhD in Engineering, 5+ years in mathematical modeling and data science
  • 🚀 Transitioning into roles as ML Engineer / MLOps / Applied AI R&D
  • 🤝 Open to full-time and freelance opportunities

📫 Reach Out

"Build things that matter. Learn fast. Stay curious."

Pinned Loading

  1. GMM-VAE GMM-VAE Public

    Gaussian Mixture Variational Autoencoder: this project implements a variant of Variational AutoEncoder (VAE) with Gaussian Mixture as a prior distribution.

    Jupyter Notebook 2

  2. L1BSR L1BSR Public

    Forked from centreborelli/L1BSR

    Self-Supervised SISR for Sentinel-2 L1B Imagery

    Python 1

  3. BiGAN-based-Anomaly-Detector BiGAN-based-Anomaly-Detector Public

    Anomaly detector based on BiGAN architecture.

    Python

  4. Expectation-Maximization Expectation-Maximization Public

    Expectation-Maximization algorithm explained with application on MNIST dataset

    Python

  5. Neural-E-M- Neural-E-M- Public

    A non official implementation of the paper : https://proceedings.neurips.cc/paper_files/paper/2017/file/d2cd33e9c0236a8c2d8bd3fa91ad3acf-Paper.pdf

    Python