ABOUT ME


I am a PhD student in Computing Science, part of the Intelligent Systems group at the Bernouilli Institute for Mathematics, Computer Science and Artificial Intelligence at the University of Groningen. My project combines machine learning methods with aspects from system identification and differential geometry to achieve explainable results.


Read More

RECENT PUBLICATIONS


'Hidden unit specialization in layered neural networks: ReLU vs. sigmoidal activation' (November 2020)

Elisa Oostwal, Michiel Straat, Michael Biehl. In: Physica A: Statistical Mechanics and its Applications, Volume 564.


ABSTRACT: By applying concepts from the statistical physics of learning, we study layered neural networksof rectified linear units (ReLU). The comparison with conventional, sigmoidal activation functions is in the center of interest. We compute typical learning curves for large shallow networks with K hidden units in matching student teacher scenarios. The systems undergo phase transitions, i.e. sudden changes of the generalization performance via the process of hidden unit specialization at critical sizes of the training set. Surprisingly, our results show that the training behavior of ReLU networks is qualitatively different from that of networks with sigmoidal activations.


Read More

RECENT TALKS

Poster

April 10-11, 2023

Efficient Informed Posterior Construction for Partially Observed Dynamical Systems

Presentation

September 12-16, 2022

Informed Posterior Construction for Partially Observed Dynamical Systems

Presentation

August 22-24, 2022

Informed Posterior Construction for Partially Observed Dynamical Systems