Gesina Schwalbe

Concept Embedding Analysis: A Review

Mar 25, 2022
Gesina Schwalbe

Figure 2 for Concept Embedding Analysis: A Review

Figure 3 for Concept Embedding Analysis: A Review

Figure 4 for Concept Embedding Analysis: A Review

* 47 pages, 6 tables, 4 figures; submitted to Artificial Intelligence Review

Access Paper or Ask Questions

Concept Embeddings for Fuzzy Logic Verification of Deep Neural Networks in Perception Tasks

Jan 03, 2022
Gesina Schwalbe, Christian Wirth, Ute Schmid

Figure 2 for Concept Embeddings for Fuzzy Logic Verification of Deep Neural Networks in Perception Tasks

Figure 3 for Concept Embeddings for Fuzzy Logic Verification of Deep Neural Networks in Perception Tasks

Figure 4 for Concept Embeddings for Fuzzy Logic Verification of Deep Neural Networks in Perception Tasks

* 21 pages (including 11 pages supplemental material), 11 Figures, 9 Tables

Access Paper or Ask Questions

Expressive Explanations of DNNs by Combining Concept Analysis with ILP

May 16, 2021
Johannes Rabold, Gesina Schwalbe, Ute Schmid

Figure 2 for Expressive Explanations of DNNs by Combining Concept Analysis with ILP

Figure 3 for Expressive Explanations of DNNs by Combining Concept Analysis with ILP

Figure 4 for Expressive Explanations of DNNs by Combining Concept Analysis with ILP

* 14 pages, 4 figures; Camera-ready submission to KI2020; The final authenticated publication is available online at https://doi.org/10.1007/978-3-030-58285-2_11; code available at https://github.com/mc-lovin-mlem/concept-embeddings-and-ilp/tree/ki2020

Access Paper or Ask Questions

XAI Method Properties: A (Meta-)study

May 15, 2021
Gesina Schwalbe, Bettina Finzel

Figure 2 for XAI Method Properties: A (Meta-)study

Figure 3 for XAI Method Properties: A (Meta-)study

Figure 4 for XAI Method Properties: A (Meta-)study

* 37 pages, 2 figures, submitted to Data Mining and Knowledge Discovery

Access Paper or Ask Questions

Verification of Size Invariance in DNN Activations using Concept Embeddings

May 14, 2021
Gesina Schwalbe

Figure 2 for Verification of Size Invariance in DNN Activations using Concept Embeddings

Figure 3 for Verification of Size Invariance in DNN Activations using Concept Embeddings

Figure 4 for Verification of Size Invariance in DNN Activations using Concept Embeddings

* 12 pages, 7 figures; Camera-ready version for AIAI2021

Access Paper or Ask Questions

Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety

Apr 29, 2021
Sebastian Houben, Stephanie Abrecht, Maram Akila, Andreas Bär, Felix Brockherde, Patrick Feifel, Tim Fingscheidt, Sujan Sai Gannamaneni, Seyed Eghbal Ghobadi, Ahmed Hammam, Anselm Haselhoff, Felix Hauser, Christian Heinzemann, Marco Hoffmann, Nikhil Kapoor, Falk Kappel, Marvin Klingner, Jan Kronenberger, Fabian Küppers, Jonas Löhdefink, Michael Mlynarski, Michael Mock, Firas Mualla, Svetlana Pavlitskaya, Maximilian Poretschkin, Alexander Pohl, Varun Ravi-Kumar, Julia Rosenzweig, Matthias Rottmann, Stefan Rüping, Timo Sämann, Jan David Schneider, Elena Schulz, Gesina Schwalbe, Joachim Sicking, Toshika Srivastava, Serin Varghese, Michael Weber, Sebastian Wirkert, Tim Wirtz, Matthias Woehrle

* 94 pages

Access Paper or Ask Questions