Sebastian Lapuschkin

发表

Understanding Image Captioning Models beyond Visualizing Attention pdf

Alexander Binder, Wojciech Samek, Jiamei Sun, 2020, ArXiv.

Unmasking Clever Hans predictors and assessing what machines really learn

Alexander Binder, Klaus-Robert Müller, Wojciech Samek, 2019, Nature Communications.

A public dataset of overground walking kinetics and full-body kinematics in healthy adult individuals

Klaus-Robert Müller, Wojciech Samek, Sebastian Lapuschkin, 2019 .

Towards Best Practice in Explaining Neural Network Decisions with LRP

Shinichi Nakajima, Alexander Binder, Wojciech Samek, 2019, 2020 International Joint Conference on Neural Networks (IJCNN).

Explaining Machine Learning Models for Clinical Gait Analysis

Wojciech Samek, Sebastian Lapuschkin, Brian Horsak, 2019, ACM Trans. Comput. Heal..

Analyzing ImageNet with Spectral Relevance Analysis: Towards ImageNet un-Hans'ed pdf

Wojciech Samek, Sebastian Lapuschkin, Klaus-Robert Müller, 2019, ArXiv.

Interpreting the Predictions of Complex ML Models by Layer-wise Relevance Propagation pdf

Alexander Binder, Klaus-Robert Müller, Wojciech Samek, 2016, ArXiv.

Explanation-Guided Training for Cross-Domain Few-Shot Classification pdf

Alexander Binder, Wojciech Samek, Ngai-Man Cheung, 2020, 2020 25th International Conference on Pattern Recognition (ICPR).

Interpreting and Explaining Deep Neural Networks for Classification of Audio Signals pdf

Klaus-Robert Müller, Wojciech Samek, Sebastian Lapuschkin, 2018, ArXiv.

Evaluating the Visualization of What a Deep Neural Network Has Learned

Alexander Binder, Klaus-Robert Müller, Wojciech Samek, 2015, IEEE Transactions on Neural Networks and Learning Systems.

iNNvestigate neural networks!

Klaus-Robert Müller, Wojciech Samek, Sebastian Lapuschkin, 2018, J. Mach. Learn. Res..

Toward Interpretable Machine Learning: Transparent Deep Neural Networks and Beyond pdf

Wojciech Samek, Sebastian Lapuschkin, Klaus-Robert Müller, 2020, ArXiv.

On the Understanding and Interpretation of Machine Learning Predictions in Clinical Gait Analysis Using Explainable Artificial Intelligence pdf

Wojciech Samek, Sebastian Lapuschkin, Brian Horsak, 2019, ArXiv.

Understanding and Comparing Deep Neural Networks for Age and Gender Classification

Alexander Binder, Wojciech Samek, Sebastian Lapuschkin, 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution pdf

Alexander Binder, Wojciech Samek, Sebastian Lapuschkin, 2020, ArXiv.

Revealing the unique features of each individual’s muscle activation signatures (Short) Unique features of muscle activation signatures

Sebastian Lapuschkin, Fabian Horst, Lilian Lacourpaille, 2020, bioRxiv.

Opening the machine learning black box with Layer-wise Relevance Propagation

Sebastian Lapuschkin, S. Lapuschkin, 2019 .

Resolving challenges in deep learning-based analyses of histopathological images using explanation methods

Klaus-Robert Müller, Wojciech Samek, Sebastian Lapuschkin, 2019, Scientific Reports.

Interpretable human action recognition in compressed domain

Klaus-Robert Müller, Wojciech Samek, Cornelius Hellge, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

How to iNNvestigate neural networks' predictions!

Klaus-Robert Müller, Wojciech Samek, Sebastian Lapuschkin, 2018 .

The LRP Toolbox for Artificial Neural Networks

Alexander Binder, Klaus-Robert Müller, Wojciech Samek, 2016, J. Mach. Learn. Res..

Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning pdf

Wojciech Samek, Sebastian Lapuschkin, Klaus-Robert Müller, 2019, Pattern Recognit..

Explaining nonlinear classification decisions with deep Taylor decomposition

Alexander Binder, Wojciech Samek, Sebastian Lapuschkin, 2015, Pattern Recognit..

Finding and Removing Clever Hans: Using Explanation Methods to Debug and Improve Deep Models

Wojciech Samek, Sebastian Lapuschkin, Klaus-Robert Muller, 2019 .

Layer-Wise Relevance Propagation for Neural Networks with Local Renormalization Layers

Alexander Binder, Wojciech Samek, Sebastian Lapuschkin, 2016, ICANN.

Explaining the unique nature of individual gait patterns with deep learning

Klaus-Robert Müller, Wojciech Samek, Sebastian Lapuschkin, 2018, Scientific Reports.

Layer-Wise Relevance Propagation: An Overview

Klaus-Robert Müller, Wojciech Samek, Sebastian Lapuschkin, 2019, Explainable AI.

What is Unique in Individual Gait Patterns? Understanding and Interpreting Deep Learning in Gait Analysis pdf

Klaus-Robert Müller, Wojciech Samek, Sebastian Lapuschkin, 2018, ArXiv.

Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning pdf

Klaus-Robert Müller, Wojciech Samek, Sebastian Lapuschkin, 2019, Pattern Recognit..

Finding and removing Clever Hans: Using explanation methods to debug and improve deep models

Wojciech Samek, Sebastian Lapuschkin, David Neumann, 2019, Inf. Fusion.

ECQx: Explainability-Driven Quantization for Low-Bit and Sparse DNNs pdf

Wojciech Samek, Sebastian Lapuschkin, Daniel Becking, 2020, xxAI@ICML.

Explain and improve: LRP-inference fine-tuning for image captioning models

Alexander Binder, Wojciech Samek, Sebastian Lapuschkin, 2020, Inf. Fusion.

ECQ$^{\text{x}}$: Explainability-Driven Quantization for Low-Bit and Sparse DNNs

Wojciech Samek, Sebastian Lapuschkin, Daniel Becking, 2021 .

Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy pdf

Klaus-Robert Müller, Wojciech Samek, Sebastian Lapuschkin, 2021, ArXiv.

Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution

Alexander Binder, Wojciech Samek, Sebastian Lapuschkin, 2020, 2020 25th International Conference on Pattern Recognition (ICPR).

Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications

Klaus-Robert Müller, Wojciech Samek, Sebastian Lapuschkin, 2021, Proceedings of the IEEE.