Skip to content
View AlexandreAbraham's full-sized avatar
61 followers · 9 following

Achievements

Achievement: YOLOAchievement: QuickdrawAchievement: Pair ExtraordinaireAchievement: Pull Sharkx3Achievement: Arctic Code Vault ContributorAchievement: Starstruck

Achievements

Achievement: YOLOAchievement: QuickdrawAchievement: Pair ExtraordinaireAchievement: Pull Sharkx3Achievement: Arctic Code Vault ContributorAchievement: Starstruck

Block or report AlexandreAbraham

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, 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
AlexandreAbraham/README.md

👋 Hi, I’m Alexandre Abraham

Website LinkedIn Google Scholar Medium Twitter

I’m a researcher and engineer working on what falls under my hands like tabular deep learning, bias correction in medical studies, and active learning. Currently building open-source tools at Neuralk‑AI.

🚀 Current work: Neuralk‑AI

  • TabBench – Benchmark suite for real-world tabular ML models: easy plug-in with industrial datasets (e‑commerce, product categorization, etc.)
  • Neuralk Foundry CE – Modular ML pipelines to support benchmarking, cross-validation, lazy loading, reproducibility.

🔬 Bias correction in medical studies

  • PopMatch – Tool for bias correction in observational medical studies.

🎯 Active Learning

  • Cardinal – A metrics‑based active learning framework by Dataiku Research.
  • OpenAL – Evaluation and interpretation framework for active learning strategies.

Pinned Loading

  1. Neuralk-AI/TabBench Neuralk-AI/TabBench Public

    TabBench is a benchmark built to evaluate machine learning models on tabular data, focusing on real-world industry use cases.

    Jupyter Notebook 100 1

  2. dataiku-research/cardinal dataiku-research/cardinal Public

    A practical Active Learning python package with a strong focus on experiments.

    Python 51 6

  3. Neuralk-AI/NeuralkFoundry-CE Neuralk-AI/NeuralkFoundry-CE Public

    The Community Edition of the Neuralk Foundry platform

    Python 47 4

  4. popmatch popmatch Public

    Experiments on pairing populations

    Python

  5. OpenAL OpenAL Public

    Forked from dataiku-research/OpenAL

    Benchmarking active learning on tabular datasets

    Jupyter Notebook