Olivier Bernard

Introduction to Bayesian inference

2026-02-08T00:00:00+01:00

This post is intended for readers who want to understand the theoretical concepts behind Bayesian inference and its applications in deep learning, including variational inference (e.g., VAEs) and amortized simulation-based inference (e.g., tabPFN).

You can access to this post by clicking on the image below.

The denoising diffusion probabilistic models (DDPM) paradigm demystified

2023-12-12T00:00:00+01:00

This post is aimed at those who want to understand the mathematical framework of denoising diffusion probabilistic model and its implementation in deep learning.

You can access to this post by clicking on the image below.

What about the conditional variational autoencoder?

2022-09-28T00:00:00+02:00

In this post I explain the mathematics behind conditional variational autoencoders and the differences with conventional variational autoencoders.

You can access to this post by clicking on the image below.

The variational autoencoder paradigm demystified

2022-09-12T00:00:00+02:00

This post is aimed at those who want to understand the mathematical framework of variational autoencoders and its implementation in deep learning.

You can access to this post by clicking on the image below.

The beauty of contrastive learning: a new step toward efficient unsupervised learning

2022-07-09T00:00:00+02:00

The aim of this post is to present the key stages/concepts of contrastive learning.

You can access to this post by clicking on the image below.

The transformer paradigm demystified

2022-06-20T00:00:00+02:00

Are you interested in understanding the mathematics that underlie the transformer? If so, this post is tailored for you!

You can access to this post by clicking on the image below.