Blog

Boltzmann + the machine

Posted on November 7, 2025

After the previous post on energy-based models (EBMs) and the Boltzmann distribution, we will now explore a classical family of such generative models. They are known as Boltzmann machines and have played an important role in the development of neural networks. Notably, the 2024 Nobel Prize in Physics was awarded... [Read More]

Tags:

Boltzmann & ML

Posted on October 28, 2025

There are intriguing connections between machine learning and physics. A full appreciation of those formal relationships and analogies is probably beyond my little (remaining) understanding of physics, and certainly very much beyond the scope of this post. We focus on the Boltzmann distribution in statistical physics, the softmax function and... [Read More]

Tags:

How to post notebooks?

Posted on December 15, 2024

It turns out that blog-posting Jupyter notebooks with Jekyll (and the Beautiful Jekyll theme) is enjoyably simple. One just needs to follow the instructions below. [Read More]

Tags:

Denoising diffusion models

Posted on December 12, 2024

A brief introduction to generative diffusion modeling is provided in this blog post. In particular, the discussion focuses on the denoising diffusion probabilistic model (DDPM) [Sohl-Dickstein et al., 2015; Ho et al., 2020]. The relation to other generative modeling approaches such as energy-based models (EBMs), variational autoencoders (VAEs) or normalizing... [Read More]

Tags:

Variational autoencoder

Posted on December 11, 2024

This blog post contains a tutorial on the variational autoencoder (VAE). Since its introduction by [Kingma and Welling, 2014, Rezende et al., 2014], the framework has received much attention for its generative modeling and representation learning capabilities. Recent reviews are given in [Doersch, 2016, Kingma and Welling, 2019, Wei et... [Read More]

Tags:

GP models

Posted on December 10, 2024

An introduction to Gaussian process modeling is given in this short note. Gaussian processes for example enable regression with built-in uncertainty quantification. [Read More]

Tags:

Physics-informed neural nets

Posted on December 9, 2024

The idea of using neural networks (NNs) for solving partial differential equations (PDEs) has been around for some time [Dissanayake and Phan-Thien, 1994; Lagaris et al., 1998]. Following the advances in fields like computer vision and natural language processing, NNs have recently enjoyed growing interest in computational science and engineering,... [Read More]

Tags:

Attention mechanism

Posted on December 8, 2024

This blog post gives a brief introduction to attention in deep neural nets. Attention establishes a mechanism that allows a model to make predictions based on selectively attending to different items of an input sequence. It can be employed as a pretty generic modeling layer for problems with a sequential... [Read More]

Tags:

Contrastive learning

Posted on December 7, 2024

This blog post provides an overly brief introduction to contrastive representation learning. In particular, we restrict the discussion to the contrastive loss [Hadsell et al., 2006] and the triplet loss [Schroff et al., 2015]. A more comprehensive review can be found in [Le-Khac et al., 2020]. A common field of... [Read More]

Tags:

Adversarial ML

Posted on December 6, 2024

The existence of adversarial examples for neural networks has been first observed in the context of image classification [Szegedy et al., 2014]. There are many great review papers on adversarial attacks and corresponding defenses. For example, the following publications are open access: [Ren et al., 2020; Khamaiseh et al., 2022;... [Read More]

Tags:

Welcome!

Posted on November 28, 2024

This is my attempt at starting a blog. It will be mainly concerned with machine learning, neural networks, computer vision and generative AI. Further topics could include music, biking or parenting. Watch out, you may encounter irony!