Evan Greven — research in machine learning and artificial intelligence

Projects

Experiment. To understand. Build.

See all projects

AI learning platform

DeepLearn

Classes adapted to your level, a workshop to build and train your networks, then an arena to put them to the test. The duels and the Elo ranking give a concrete objective to learning.

Classification of exoplanet candidates

Exoplanet Hunter

An application for ranking exoplanet candidates and reviewing their predictions. The project opens a thesis axis: developing a Transformer from scratch combining light curves, physical data and TSFRESH statistics.

View on GitHub

Deep Reinforcement Learning and tree search

Reinforcement gaming agents

Implementation of DQN, Double DQN and REINFORCE, compared to move search methods. The presentation details the models, the results and their limitations, then allows you to observe them in play or to confront them.

View on GitHub

Unsupervised learning

Understanding latent space

Exploring the latent space: a representation where a few coordinates summarize an image. With PCA, autoencoders and VAEs, the experiments and workshops show how this space is built, what it preserves and what happens when we move there.

View on GitHub

Design of an industrializable RAG

Documentary and statistical assistant

A wizard for non-sensitive data, designed for enterprise deployment. It combines large models, documentary research, calculations and maps by limiting the information transmitted to the API. The technical choices and methods of verifying the results are detailed in the project presentation.

View on GitHub

Tabular methods and planning

Reinforcement learning

Study of Q-learning, SARSA, Monte Carlo and Dyna-Q, with a reference to dynamic programming. From grids to Monty Hall, experiments allow you to compare exploration, rewards and strategies, then train an agent.

View on GitHub

Implementation from scratch

Machine learning library

A Rust library accessible from Python, with training, prediction and saving of models. The presentation explains calculations and backpropagation; a workshop allows you to compare decision boundaries on 2D data.

View on GitHub

DeepLearn — 1 on 7

Hover to exploreTap to preview, then tap to read

Research

Learn from the world
and learn to question it.

Latent dynamics guided by knowledge.

Investigate how explicit knowledge can make prediction more sample-efficient and generalisable, while learning when to trust it.

Explore the idea

Articles

Understand. Then transmit.

Explore the blog

Coming soon

The journal continues.

Coming soon

The journal continues.

Understanding Transformers — 1 on 3

Portrait of Evan Greven carved in a silvery stone with eroded contours.

About

Curiosity like
common thread.

Data Scientist · ML Engineer

Understand how models learn, experience and share. I start from concrete problems to explore their mechanisms and their limits.

My journey

Get in touch

Let's write together.

Send message

All fields are required.

This form prepares an email in your email application; you choose whether to send it. Evan Greven uses the information received to respond to your enquiry. Data and rights.