We are off to NeurIPS 2024 in Vancouver, Canada!

We are excited to share that one of our research papers has been accepted to a workshop at the renowned Conference on Neural Information Processing Systems (NeurIPS 2024)! As a leading global event in machine learning and artificial intelligence, NeurIPS brings together the brightest minds in the field. We look forward to presenting our work and engaging with the research community during the workshop sessions from December 10th to 15th, 2024. More info can be found on the official page of NeurIPS 2024. The accepted paper from our team and a brief overview are as follows:

Zhuo Cao, Lena Krieger, Hanno Scharr, and Ira Assent. "Galaxy Morphology Classification with Counterfactual Explanation." In Advances in Neural Information Processing Systems，NeurIPS 2024 ML4PS Workshop.

Galaxy morphologies play an essential role in the study of the evolution of galaxies. The determination of morphologies is laborious for a large amount of data giving rise to machine learning-based approaches. Unfortunately, most of these approaches offer no insight into how the model works and make the results difficult to understand and explain. We here propose to extend a classical encoder-decoder architecture with invertible flow, allowing us to not only obtain a good predictive performance but also provide additional information about the decision process with counterfactual explanations.

Stay tuned for more details about our presentation at NeurIPS 2024!