Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Joachim Sicking

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

Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilities


Apr 22, 2021
Julia Rosenzweig, Joachim Sicking, Sebastian Houben, Michael Mock, Maram Akila

* Under IEEE Copyright; accepted at the SAIAD (Safe Artificial Intelligence for Automated Driving) Workshop at CVPR 2021 

  Access Paper or Ask Questions

Approaching Neural Network Uncertainty Realism


Jan 08, 2021
Joachim Sicking, Alexander Kister, Matthias Fahrland, Stefan Eickeler, Fabian Hüger, Stefan Rüping, Peter Schlicht, Tim Wirtz

* Accepted at the NeurIPS 2019 Workshop on Machine Learning for Autonomous Driving (ML4AD) 

  Access Paper or Ask Questions

A Novel Regression Loss for Non-Parametric Uncertainty Optimization


Jan 07, 2021
Joachim Sicking, Maram Akila, Maximilian Pintz, Tim Wirtz, Asja Fischer, Stefan Wrobel

* Accepted at the 3rd Symposium on Advances in Approximate Bayesian Inference (AABI), code is available on: https://github.com/fraunhofer-iais/second-moment-loss. arXiv admin note: substantial text overlap with arXiv:2012.12687 

  Access Paper or Ask Questions

Second-Moment Loss: A Novel Regression Objective for Improved Uncertainties


Dec 23, 2020
Joachim Sicking, Maram Akila, Maximilian Pintz, Tim Wirtz, Asja Fischer, Stefan Wrobel

* Code is available on: https://github.com/fraunhofer-iais/second-moment-loss 

  Access Paper or Ask Questions

DenseHMM: Learning Hidden Markov Models by Learning Dense Representations


Dec 17, 2020
Joachim Sicking, Maximilian Pintz, Maram Akila, Tim Wirtz

* Accepted at LMRL workshop at NeurIPS 2020. Code is available on: https://github.com/fraunhofer-iais/dense-hmm 

  Access Paper or Ask Questions

Characteristics of Monte Carlo Dropout in Wide Neural Networks


Jul 10, 2020
Joachim Sicking, Maram Akila, Tim Wirtz, Sebastian Houben, Asja Fischer

* Accepted at the ICML 2020 workshop for Uncertainty and Robustness in Deep Learning 

  Access Paper or Ask Questions

Efficient Decentralized Deep Learning by Dynamic Model Averaging


Jul 09, 2018
Michael Kamp, Linara Adilova, Joachim Sicking, Fabian Hüger, Peter Schlicht, Tim Wirtz, Stefan Wrobel


  Access Paper or Ask Questions