Michiel Straat

PhD Student Intelligent Systems

University of Groningen

Welcome

I am a PhD student in the Intelligent Systems group at the Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence. In the project, we use techniques from statistical physics to analyze the learning behavior of machine learning models and get more insight into practically relevant phenomena, which can be used to improve machine learning algorithms.

Research Interests

Machine Learning
Computational Intelligence
Statistical Physics
Data Science

Recent Publications

Learning Vector Quantization and relevances in complex coefficient space

In this contribution, we consider the classification of time series and similar functional data which can be represented in complex …

Michiel Straat, Marika Kaden, Matthias Gay, Thomas Villmann, Alexander Lampe, Udo Seiffert, Michael Biehl, Friedrich Melchert

PDF DOI

On-line learning dynamics of ReLU neural networks using statistical physics techniques

We introduce exact macroscopic on-line learning dynamics of two-layer neural networks with ReLU units in the form of a system of …

Michiel Straat, Michael Biehl

PDF

Statistical Mechanics of On-Line Learning Under Concept Drift

We introduce a modeling framework for the investigation of on-line machine learning processes in non-stationary environments. We …

Michiel Straat, Fthi Abadi, Christina Göpfert, Barbara Hammer, Michael Biehl

PDF DOI

Prototypes and matrix relevance learning in complex Fourier space

In this contribution, we consider the classification of time-series and similar functional data which can be represented in complex …

Michiel Straat, Marika Kaden, Matthias Gay, Thomas Villmann, Alexander Lampe, Udo Seiffert, Michael Biehl, Friedrich Melchert

PDF DOI

Segmentation of blood vessels in retinal fundus images

In recent years, several automatic segmentation methods have been proposed for blood vessels in retinal fundus images, ranging from …

Michiel Straat, Jorrit Oosterhof

PDF

Recent & Upcoming Talks

On-line learning dynamics of ReLU neural networks using statistical physics techniques

Apr 26, 2019 11:40 AM European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning - ESANN 2019

Slides

Online Learning Dynamics of ReLU Neural Networks

Mar 29, 2019 2:30 PM Second International Workshop on Intelligent Systems and Computational Intelligence - WISCI 2019

On-line learning in neural networks with ReLU activations

The rectifier activation function (Rectified Linear Unit: ReLU) has become popular in deep learning applications, mostly because the …

Sep 19, 2018 1:30 PM Graduation Colloquium

Slides

Prototypes and matrix relevance learning in complex Fourier space

Jun 29, 2017 11:40 AM 12th International Workshop on Self-Organizing Maps and Learning Vector Quantization, Clustering and Data Visualization - WSOM+ 2017

Slides

Segmentation of blood vessels in retinal fundus images

The inspection of the blood vessel tree in the fundus, which is the interior surface of the eye opposite to the lens, is important in …

Apr 7, 2017 9:05 AM 14th sc@RUG

Michiel Straat, Jorrit Oosterhof

Slides

Teaching

Past and upcoming teaching assistant positions include:

Information Security (2016 and 2017)
Advanced Algorithms and Data Structures (2019)

Michiel Straat

PhD Student Intelligent Systems

University of Groningen

Welcome

Research Interests

Previous

Recent Publications

Learning Vector Quantization and relevances in complex coefficient space

On-line learning dynamics of ReLU neural networks using statistical physics techniques

Statistical Mechanics of On-Line Learning Under Concept Drift

Prototypes and matrix relevance learning in complex Fourier space

Segmentation of blood vessels in retinal fundus images

Recent & Upcoming Talks

On-line learning dynamics of ReLU neural networks using statistical physics techniques

Online Learning Dynamics of ReLU Neural Networks

On-line learning in neural networks with ReLU activations

Prototypes and matrix relevance learning in complex Fourier space

Segmentation of blood vessels in retinal fundus images

Teaching

Contact