I am a first year PhD student in Machine Learning at the University of Amsterdam, supervised by Prof. Max Welling. I am interested in self-supervised representation learning, focussing on mutual information maximization approaches and on structured representations.
Before finding my way into Machine Learning, I completed a BSc in Cognitive Science at the University of Tübingen. During this study, I worked at the Max Planck Institute for Biological Cybernetics conducting research on the representation of visual percepts in the neuronal activity of rodents. After completing a BSc in Informatics at the University of Tübingen, I graduated with a MSc in Artificial Intelligence at the University of Amsterdam.
Sindy Löwe*, Peter O'Connor, Bastiaan S. Veeling*
We show that we can train a neural network without end-to-end backpropagation and achieve competitive performance.
[Link, PDF(arXiv), Code]
An earlier version of this paper was accepted at the ICML Workshop for Self-Supervised Learning (2019).
[PDF, Link to Workshop Site]
Master's Thesis (2019)
Resulted in publication:
"Putting An End to End-to-End: Gradient-Isolated Learning of Representations"
Paul Bergmann, Sindy Löwe, Michael Fauser, David Sattlegger, Carsten Steger
Illustrating the shortcomings of pixel-wise reconstruction errors when using autoencoders for unsupervised defect segmentation on image data and proposing to use a perceptual loss based on structural similarity.
Extended Abstract at Neuroscience 2015
Sindy Löwe, Masataka Watanabe, Nikos Logothetis, Laura Busse, Steffen Katzner
Investigating how temporal predictability affects the processing of a visual stimulus by measuring the responses of single neurons in the mouse primary visual cortex (V1).
LOEWE [dot] SINDY [at] GMAIL [dot] com
AMLab, University of Amsterdam
Science Park 904, 1098 XH Amsterdam, The Netherlands© 2019 Sindy Löwe Design: Free CSS