AI Helpers

Warith Harchaoui, Mohamed Chelali, Bachir Zerroug

AI Helpers is a suite of Python libraries (under BSD License) designed to streamline and improve artificial intelligence (AI) development. Whether you're working on machine learning, computer vision, or natural language processing (NLP), AI Helpers offers utility tools to simplify common tasks in AI-driven projects.

✒️ 💻 Tech Tips

Programming in AI

Warith Harchaoui, Mohamed Chelali, Matias Tassano and Pierre-Louis Antonsanti

The aim of this webpage is to present a basic cheat sheet for programming in Machine Learning (i.e. Statistical Learning, Pattern Recognition, Artificial Intelligence, Data Science) for tremendous applications such as in Computer Vision, Sound Processing and Natural Language Processing.

✒️ 💻 Tech Tips

Dear Teacher

Collège Stanislas, 2021
Warith Harchaoui

Dear Professor,

On the second day of March in the year 2021, my friend Quentin and I paid you a visit in prep school Stanislas in Paris to express our gratitude on behalf of many students for imparting upon us the satisfaction mark. For almost two decades, I have made use of this punctuation, and it has made me feel as though I belong to a guild of enlightened scholars, much like yourself, who continue to teach us even today. [...]

✒️ ❤️ Inspirational Teacher

Value in Data

Think Tank 4^eRévolution, 2021
Warith Harchaoui and Laurent Pantanacce

Each industrial revolution is driven by a driving force: a raw material, an energy source, a creative technology that redefines the economy. Since the 19th century, we can list steam, coal, oil, electricity, radio, the transistor, computers, and today artificial intelligence (AI). This fourth industrial revolution is troubling because its commodity is abstract: data. At the scale of humanity, this seems a more significant milestone than a means of communication such as radio or the Internet. [...]

✒️ 🧐 White Paper

AI for Business

Rennes School of Buiness, 2021-2024
Warith Harchaoui and Laurent Pantanacce

Filling the gap between AI tech people and team leaders. This course is designed to help business leaders understand the AI business aspects and how to implement it in their organizations. Two seasoned practioners of Scientific and Corporate AI teach the basics of AI for reconciliation of science and business for the sake of company's success.

✒️ 👨‍🏫 Executive MBA

On Refait le Mac avec Luc Julia, le Papa de Siri 🇫🇷

Electric Dreams, 2020
Olivier Frigara, Luc Julia and Warith Harchaoui

Luc Julia is the special guest on On refait le Mac. This Frenchman, co-creator of Siri, takes a look at his baby and why Apple's voice assistant is having so much trouble growing up. This world expert in artificial intelligence questions its real impact on our future. Should we believe the tech giants who predict that it will revolutionise everything? Should we be afraid? Let's debate!

✒️ 📺 ORLM

An Introduction to Neural Networks for Statisticians 🇫🇷

Université Paris Descartes, École 42, 2020
Warith Harchaoui

From a single neuron, to a layer of neurons, then several layers, sometimes convolutional, and even several opposing neural networks, we are seeing certain aspects of the mystery of intelligence emerge through a technology that is changing the game in almost every area of our contemporary world.

✒️ 🧑‍🏫 Conference

Favorite Books in Artificial Intelligence

Warith Harchaoui

In the rapidly advancing field of Artificial Intelligence, it is common to observe high volume and pace of both scientific and non-scientific publications. It is overwhelming and I am often asked how to do.
It is in this context that I present a list of books that I find particularly noteworthy, along with some comments, for those readers who are eager to engage in the exciting AI adventure.

✒️ 📚 Books

Optimal transport-based machine learning to match specific patterns: application to the detection of molecular regulation patterns in omics data

Journal of the Royal Statistical Society (RSS), 2024
Thi Thanh Yen Nguyen, Warith Harchaoui, Lucile Mégret, Cloe Mendoza, Olivier Bouaziz, Christian Neri and Antoine Chambaz

We have created methods for geometrically connecting two piles of points, which is useful when these points are supposed to match. Our application example concerns the study of messenger RNA in genetics to understand Huntington's disease.

🗞️ 🧬 Paper

Generalised Mutual Information for Discriminative Clustering

Neural Information Processing Systems (NEURIPS), 2023
Louis Ohl, Pierre-Alexandre Mattei, Charles Bouveyron, Warith Harchaoui, Mickaël Leclercq, Arnaud Droit and Frederic Precioso

Clustering is the process of making groups among objects: similar within a group, dissimilar between two groups. The human mind naturally likes to form groups when it comes to customers, genes, fruits, animals and so on. The GEMINI project exploits artificial neural networks in a novel way for this large-scale task.

🗞️ ♊️ Paper

Learning Representations using Neural Networks and Optimal Transport 🇫🇷🇬🇧

Ph.D. in Applied Mathematics, 2020
Warith Harchaoui
(supervised by Pr. Charles Bouveyron and Dr. Stéphane Raux)

From 2016 to 2020, this Ph.D. work focused on three key areas:

• Clustering: grouping large-scale data in number and dimension ;
• Importance of data features: identifying representative and discriminating features in data without the need for manual labels ;
• Confidence level estimation in automated decisions: creating statistical methods to assess the reliability of automated decisions, which is crucial in industry, security and healthcare.
‍

The originality of this research lies in the way it combines the mathematical fields of optimal transportation and neural networks in particular with generative artificial intelligence, which was in its infancy.

🗞️ 🎓 Ph.D. Defense