20 citations · 66 across the 10 of their papers we have counts for
4 papers · 1 filter
Scaling Dimension
Bernhard Ganter, Tom Hanika, Johannes Hirth
Conceptual Scaling is a useful standard tool in Formal Concept Analysis and beyond. Its mathematical theory, as elaborated in the last chapter of the FCA monograph, still has room…
Conceptual Views on Tree Ensemble Classifiers
Tom Hanika, Johannes Hirth
Random Forests and related tree-based methods are popular for supervised learning from table based data. Apart from their ease of parallelization, their classification performance…
Conceptual Views of Neural Networks: A Framework for Neuro-Symbolic Analysis
Johannes Hirth, Tom Hanika
We introduce \emph{conceptual views} as a formal framework grounded in Formal Concept Analysis for globally explaining neural networks. Experiments on twenty-four ImageNet models a…
Quantifying the Conceptual Error in Dimensionality Reduction
Tom Hanika, Johannes Hirth
Dimension reduction of data sets is a standard problem in the realm of machine learning and knowledge reasoning. They affect patterns in and dependencies on data dimensions and ult…