We are the Machine Learning Group led by Prof. Barbara Hammer at Bielefeld University.
On this page you can find the accompanying source code of our publications 😃
We are the Machine Learning Group led by Prof. Barbara Hammer at Bielefeld University.
On this page you can find the accompanying source code of our publications 😃
Unsupervised Unlearning of Concept Drift with Autoencoders by André Artelt, Kleanthis Malialis, Christos G. Panayiotou, Marios M. Polycarpou and Barbara Hammer
"'I do not Know! But Why?' -- Local Model-Agnostic Example-based Explanations of Reject" by André Artelt, Roel Visser and Barbara Hammer
On the computation of counterfactual explanations - A survey by André Artelt and Barbara Hammer
Evaluating Robustness of Counterfactual Explanations by André Artelt, Valerie Vaquet, Riza Velioglu, Fabian Hinder, Johannes Brinkrolf, Malte Schilling and Barbara Hammer
"Why Here and Not There?" -- Diverse Contrasting Explanations of Dimensionality Reduction by André Artelt, Alexander Schulz and Barbara Hammer.
Forked from inaamashraf/GCNs_for_WDS
Spatial Graph Convolution Neural Networks for Water Distribution Systems
A Python library for end-to-end learning on surfaces. It implements pre-processing functions that include geodesic algorithms, neural network layers that operate on surfaces, visualization tools and benchmarking functionalities.
"The Effect of Data Poisoning on Counterfactual Explanations" by André Artelt et al.
"A Two-Stage Algorithm for Cost-Efficient Multi-instance Counterfactual Explanations" by Artelt et al.
This is an implementation of the DeepView framework that was presented in the paper Schulz, A., Hinder, F., & Hammer, B. (2020): https://www.ijcai.org/Proceedings/2020/319. Also available on Arxiv (2019 version): https://arxiv.org/abs/1909.09154.
CEML - Counterfactuals for Explaining Machine Learning models - A Python toolbox
Official code for the paper: Physics-Informed Graph Neural Networks for Water Distribution Systems
Introducing the Alien Zoo approach: An experimental framework for evaluating counterfactual explanations for ML