Machine Learning

52 articles · Latest April 9, 2026

eScience Editorial Team·Apr 9, 2026

FOSDEM 2026: Observations and key takeaways

If you missed FOSDEM 2026 — the largest conference dedicated to open-source software — you can still absorb some of the experience as shared by NLeSC RSEs Flavio Hafner, Ole Mussm...

eScience Editorial Team·Mar 26, 2026

Bring Your Own Backend

A pattern for sustainable research software collaboration By Stefan Verhoeven. Image source https://www.pnnl.gov/news-media/new-nationwide-modeling-points-widespread-racial-dispari...

Bart Schilperoort·Jan 15, 2026

Use Julia to write code that runs on any GPU

Use Julia to write code that runs on any GPU 10 How to write Julia code than can run on any GPU, and why you would want to do that. As the name implies, the main use of Graphics Pr...

Carsten Schnober·Jul 10, 2025

Could AI be (in) FAIR?

Open Science is driven by FAIR principles. Made for data, adapted for software, how can they survive the current wave of "Artificial Intelligence"? Resistance from those selling it...

Flavio Hafner·Jun 27, 2025

Empirically evaluating privacy in machine learning I: Introduction

Research in the social and health sciences often relies on accessing data sourced from statistical agencies or healthcare organizations. Such data sets contain sensitive informatio...

Flavio Hafner·Jun 17, 2025

Empirically evaluating privacy in machine learning II: Hypothesis testing

Using statistics to think like a hacker, so we can avoid them! Image from page 182 of “Elements of statistics” (1954). Licensed under creative commons.This post is the second in a...

Flavio Hafner·Jun 17, 2025

Empirically evaluating privacy in machine learning III: functional & gaussian differential privacy

1 Using statistics to think like a hacker, so we can avoid them! The Greek letter lambda, symbol of functional programming.This post is the third in a series on differential privac...

ole·Feb 21, 2025

A Helpful Noob

Photo by Keiteu Ko on Unsplash Introduction Yesterday, my colleague Faruk asked me to conduct a Hallway Test for the NLeSC/python-template he is working on: he just grabbed me off...

Candace Moore·Oct 3, 2024

The magic of teaching about the anti-magic of generative AI

On the use and abuse of generative artificial intelligence by students Photo by Owen Beard on Unsplash Recently, I taught the pilot workshop Medical Image Processing in Python. The...

eScience Editorial Team·Aug 22, 2024

Research software is critical to the future of AI-driven research

By Michelle Barker, Kim Hartley, Daniel S. Katz, Richard Littauer, Qian Zhang, Shurui Zhou, Jyoti Bhogal Cross-posted from ReSA and the Digital Research Alliance of Canada Photo cr...

Christiaan Meijer·Apr 5, 2024

Masking time-series for eXplainable AI

Why did my Machine Learning (ML) model make this decision? Is it paying attention to the right elements of the data we give it? Figure 1: In the signal on the left, the spike is a...

Nicolas Renaud·Dec 6, 2023

Machine Learning Machinery for Quantum Chemistry

Machine learning techniques are impacting all areas of science, and molecular simulations are not spared. This blog post shows how to make use of the tools and techniques developed...

Kody Moodley·Nov 2, 2023

The Orange3 data mining platform for the Social Sciences and Humanities

The Orange3 data mining platform for the Social Sciences and Humanities Why aren’t more SSH researchers using and extending the platform? Orange is an open-source Python-based data...

Kody Moodley·Oct 12, 2023

the orange3 data mining platform as a research tool

Why aren’t more SSH researchers using and extending the platform? Orange is an open-source Python -based data mining application with a graphical user interface (GUI). It allows pe...

Peter Kalverla·Aug 21, 2023

Lilio — a calendar package for machine learning with time series data

Designed with the S2S community, available for everyone SubscribeRemember me for faster sign in These are just some of the questions that scientists in the field of sub-seasonal to...

Stef Smeets·Jun 20, 2023

Reduce, reuse, recycle: save the planet one GitHub action at a time

Reduce, reuse, recycle: save the planet one GitHub action at a time 53 Written by Stef Smeets and Sander van Rijn. Photo by Ralph (Ravi) Kayden on UnsplashAsk any environmentalist...

eScience

eScience Editorial Team·May 16, 2023

Creating a Community by Integrating Expertise, Tools and Ideas

A personal reflection on the first NPLinker eScience workshop for Natural Product Discovery By Justin van der Hooft This blog post is written by Wageningen University & Researc...

Aron·May 4, 2023

Molecular Simulations using Machine Learning, Part 3

24 In the first part of this series we looked at the physics of simulating molecules, and went from quantum mechanics to something that is more efficient to solve, namely density f...

Aron·Apr 13, 2023

Molecular Simulations using Machine Learning, Part 2

In this post, I will walk through the process of designing a model used in molecular simulations, from essential to state of the art. This is the second part of a series on using m...

Aron·Mar 31, 2023

Molecular Simulations using Machine Learning, Part 1

Simulation of water molecules from Wikipedia. Are you curious about how scientists study the properties of materials, proteins, and drugs? It all starts with molecular simulation....

Rob van Nieuwpoort·Mar 21, 2023

Defining the roles of research software

SubscribeRemember me for faster sign in Examples: In the biochemistry realm, software is used for modeling molecules for use in a next-gen diagnostics or therapeutics: we want to d...

Candace Moore·Feb 16, 2023

The medical chatbot will not see you now

Dr. Candace Makeda Moore, RSE and medical doctor, lays out what she believes the potential pitfalls and problems of AI chatbots in medicine are: closed source, discrimination, (ir)...

Florian Huber·Jan 31, 2023

Build a mass spectrometry analysis pipeline in Python using matchms — part II: Spec2Vec

After “part I” which gave an introduction on how to import, process, and analyze a tandem mass spectra dataset using Python and matchms, “part II” will add Spec2Vec to the game, a...

eScience

eScience Editorial Team·Dec 16, 2022

Machine Learning as a tool for political speech analysis

The following example of a sentence from Putin’s invasion-speech may clarify what CM annotation of texts involves: ‘The purpose of this operation is to protect people Effect who, f...

Sonja Georgievska·Dec 16, 2022

Small-scale initiative in Machine Learning 2021: how did it go?

Photo by "My Life Through A Lens" on Unsplash Small-scale initiative in Machine Learning 2021: how did it go? Introducing a series of blog posts on our collaborative projects in m...

Malte Lüken·Dec 13, 2022

Immaculate Speech and Hallucinations

When (not) to use OpenAI’s Whisper to transcribe audio in a social sciences project Using Whisper off-the-shelf in this case might bias the results because it tends to “polish” the...

eScience Editorial Team·Jun 13, 2022

Studying political symbolism in Turkish TV dramas with machine learning

Studying political symbolism in Turkish TV dramas with machine learning eScience Editorial Team·Jun 10, 2022 SubscribeRemember me for faster sign in Faced with a challenge of this...

eScience

eScience Editorial Team·May 23, 2022

The mystery of glass: why machine learning can help us

This blog is part of our blog series: The Small-Scale Initiative on Machine Learning, how did it go?, where groups who were invited to participate in a project with eScience Center...

Sonja Georgievska·May 13, 2022

Reusable software in the era of AI: why sometimes you must reinvent the wheel

> In traditional software development, reinventing the wheel is a cardinal sin. But AI has changed the picture. In AI-based software development the traditional reusable components...

eScience Editorial Team·May 9, 2022

A machine learning approach to laughter

SubscribeRemember me for faster sign in Our mentors at the eScience Center (Patrick Bos, Florian Huber, and Jisk Attema), provided us with practical guidance in the use of such lib...

eScience Editorial Team·Apr 22, 2022

Using machine learning to tell apart rain, snow, hail and fog from cell tower data

Using machine learning to tell apart rain, snow, hail and fog from cell tower data eScience Editorial Team·Apr 21, 2022 Next, we explored whether CMLs can be used to detect fog. Fo...

eScience

Sven van der Burg·Apr 14, 2022

A letter to my parents about my experience in a machine learning consultancy project

What does a Research Software Engineer do? This is not always easy to answer, but when your parents are asking, you definitely want to give a nice answer A fountain pen writing on...

eScience Editorial Team·Apr 11, 2022

Can machine learning help us improve stroke rehabilitation? A step towards personalized therapy

SubscribeRemember me for faster sign in Along the way, the biggest issue was our data set itself. Because data collection of human movements is a job that takes time and our patien...

eScience Editorial Team·Mar 31, 2022

How machine learning could help Simone to play Ludo

Simone is a 12 year old girl. She loves to play Ludo with her mum, dad and her little brother. However, when she pushes the dice switch in the middle of the Ludo board game, she c...

eScience Editorial Team·Mar 11, 2022

How to find your rubber duck: Using machine learning to understand a changing sea

SubscribeRemember me for faster sign in To get a quick start, they applied for the eScience Center Small-Scale Initiative (SSI), and were awarded consultancy on their project title...

eScience Editorial Team·Mar 11, 2022

Parsing Hebrew and Syriac morphology using Deep Learning

State-of-the-art technology meets ancient literature This blog is part of our blog series: The Small-Scale Initiative on Machine Learning, how did it go?, where groups who were inv...

Hanno Spreeuw·Nov 23, 2020

eScience trends from ADASS 2020

eScience trends from ADASS 2020 Scaling up compute and storage resources are not going to be the biggest hurdles. 8 My general feeling about this conference What a delight ADASS (A...

Florian Huber·Sep 1, 2020

Machine learning for research — use it or refuse it? Two flowcharts to help you decide.

Machine learning (in particular deep learning) started to become extremely hot 5–10 years ago. Now, this trend has fully reached most academic fields outside computer science as we...

Sonja Georgievska·Jun 18, 2020

Machine learning: when it is easy & when it is difficult

SubscribeRemember me for faster sign in Hey, should I draw a wild curve that splits all points exactly? But how am I sure that the curve will split properly all new points that I h...

Netherlands eScience Center·Apr 2, 2020

Can we teach AI’s speech by simulating young children’s ability to learn spoken language?

8 Today, we can´t imagine life without voice controlled intelligent systems such as Siri, Google Assistant, car navigation systems and other applications. Such systems use a speech...

Florian Huber·Feb 11, 2020

Workshop Machine Learning for Research 2020

For one full week we worked with 6 research teams from different disciplines to explore if and how machine learning could help them answer their research question(s). Here is a bri...

eScience

Florian Huber·Feb 11, 2020

Workshop Machine Learning for Research 2020 … did it work?

Evaluating our one-week hands-on workshop on applying machine learning to research. 5 Stimulate diverse teams and be aware of (gender-)biases.We wanted to attract diverse teams and...

eScience

Florian Huber·Feb 7, 2020

Monopolizing AI

The field of machine learning and AI is facing an increasing divide. Florian Huber·Feb 4, 2020 16 Last edit: 07/02/2020 It seems contradictory at first. On the one hand, deep learn...

eScience

eScience Editorial Team·Dec 9, 2019

Managing the crowd: a big data approach

Crowd disasters have taken many lives. The Love Parade disaster (Duisburg, 2010), the Ellis Park Stadium disaster (Johannesburg, 2001), the PhilSports Stadium stampede (Manila, 200...

Netherlands eScience Center·Nov 28, 2019

Accelerating the search for dark matter

Astronomical observations show that roughly 80% of the mass of the universe is made up of dark matter, a material that cannot be directly observed because emits no light or energy....

Florian Huber·Sep 24, 2019

Highlights from the European Conference on Machine Learning 2019

ML highlights and trends as seen at ECML-PKDD 2019 (16–20 September, Würzburg, Germany) The conference’s cryptic name is due to the fact that it is a merger of two conferences: the...

Sonja Georgievska·Jun 12, 2019

explainable ai exit or infinite loop

> Let us simplify before we try to explain Photo by Franck V. on Unsplash Before we start, let’s make it clear: by AI here I mean computational statistics, and by explainable — wel...

Florian Huber·Mar 4, 2019

superhuman blog post

#demystifyAI series (this small series aims at putting important AI-related aspects into perspective) Why you shouldn’t be afraid of AI tools occasionally performing superhuman in...

eScience Editorial Team·Sep 26, 2018

analyzing the ‘life’ of newspapers with machine learning

Marcel Broersma, professor of Media and Journalism Studies and Director of the Research Centre for Media and Journalism Studies (CMJS) at the University of Groningen Photography:...

Erik Tjong Kim Sang·Mar 20, 2018

active learning

Computers perform better than humans in arithmetic and chess but if there is one task in which humans are superior it is image processing. But for how long? In 2015 there was a br...

eScience Editorial Team·Jun 21, 2017

what is the impact of visualization on science

Scientific visualization impacts all research disciplines. Understanding our past, dealing with the challenges of climate change, discovering dark matter, and analyzing human behav...

Dafne van Kuppevelt·Mar 20, 2017

mcfly time series classification made easy

A deep learning approach for time series Deep learning is hot. It is the state-of-the-art method for object recognition in images and video, and was an important component of the A...

Machine Learning

FOSDEM 2026: Observations and key takeaways

Bring Your Own Backend

Use Julia to write code that runs on any GPU

Could AI be (in) FAIR?

Empirically evaluating privacy in machine learning I: Introduction

Empirically evaluating privacy in machine learning II: Hypothesis testing

Empirically evaluating privacy in machine learning III: functional &amp; gaussian differential privacy

A Helpful Noob

The magic of teaching about the anti-magic of generative AI

Research software is critical to the future of AI-driven research

Masking time-series for eXplainable AI

Machine Learning Machinery for Quantum Chemistry

The Orange3 data mining platform for the Social Sciences and Humanities

the orange3 data mining platform as a research tool

Lilio — a calendar package for machine learning with time series data

Reduce, reuse, recycle: save the planet one GitHub action at a time

Creating a Community by Integrating Expertise, Tools and Ideas

Molecular Simulations using Machine Learning, Part 3

Molecular Simulations using Machine Learning, Part 2

Molecular Simulations using Machine Learning, Part 1

Defining the roles of research software

The medical chatbot will not see you now

Build a mass spectrometry analysis pipeline in Python using matchms — part II: Spec2Vec

Machine Learning as a tool for political speech analysis

Small-scale initiative in Machine Learning 2021: how did it go?

Immaculate Speech and Hallucinations

Studying political symbolism in Turkish TV dramas with machine learning

The mystery of glass: why machine learning can help us

Reusable software in the era of AI: why sometimes you must reinvent the wheel

A machine learning approach to laughter

Using machine learning to tell apart rain, snow, hail and fog from cell tower data

A letter to my parents about my experience in a machine learning consultancy project

Can machine learning help us improve stroke rehabilitation? A step towards personalized therapy

How machine learning could help Simone to play Ludo

How to find your rubber duck: Using machine learning to understand a changing sea

Parsing Hebrew and Syriac morphology using Deep Learning

eScience trends from ADASS 2020

Machine learning for research — use it or refuse it? Two flowcharts to help you decide.

Machine learning: when it is easy &amp; when it is difficult

Can we teach AI’s speech by simulating young children’s ability to learn spoken language?

Workshop Machine Learning for Research 2020

Workshop Machine Learning for Research 2020 … did it work?

Monopolizing AI

Managing the crowd: a big data approach

Accelerating the search for dark matter

Highlights from the European Conference on Machine Learning 2019

explainable ai exit or infinite loop

superhuman blog post

analyzing the ‘life’ of newspapers with machine learning

active learning

what is the impact of visualization on science

mcfly time series classification made easy

Empirically evaluating privacy in machine learning III: functional & gaussian differential privacy

Machine learning: when it is easy & when it is difficult