Explaining deep neural networks and beyond: A review of methods and applications

W Samek, G Montavon, S Lapuschkin… - Proceedings of the …, 2021 - ieeexplore.ieee.org
With the broader and highly successful usage of machine learning (ML) in industry and the
sciences, there has been a growing demand for explainable artificial intelligence (XAI) …

Layer-wise relevance propagation: an overview

G Montavon, A Binder, S Lapuschkin, W Samek… - … and visualizing deep …, 2019 - Springer
For a machine learning model to generalize well, one needs to ensure that its decisions are
supported by meaningful patterns in the input data. A prerequisite is however for the model …

Recent progress on flexible capacitive pressure sensors: From design and materials to applications

RB Mishra, N El‐Atab, AM Hussain… - Advanced materials …, 2021 - Wiley Online Library
For decades, the revolution in design and fabrication methodology of flexible capacitive
pressure sensors using various inorganic/organic materials has significantly enhanced the …

Towards explainable artificial intelligence

W Samek, KR Müller - … AI: interpreting, explaining and visualizing deep …, 2019 - Springer
In recent years, machine learning (ML) has become a key enabling technology for the
sciences and industry. Especially through improvements in methodology, the availability of …

Unmasking Clever Hans predictors and assessing what machines really learn

S Lapuschkin, S Wäldchen, A Binder… - Nature …, 2019 - nature.com
Current learning machines have successfully solved hard application problems, reaching
high accuracy and displaying seemingly intelligent behavior. Here we apply recent …

Explaining the differences of gait patterns between high and low-mileage runners with machine learning

D Xu, W Quan, H Zhou, D Sun, JS Baker, Y Gu - Scientific reports, 2022 - nature.com
Running gait patterns have implications for revealing the causes of injuries between higher-
mileage runners and low-mileage runners. However, there is limited research on the …

Supporting artificial social intelligence with theory of mind

J Williams, SM Fiore, F Jentsch - Frontiers in artificial intelligence, 2022 - frontiersin.org
In this paper, we discuss the development of artificial theory of mind as foundational to an
agent's ability to collaborate with human team members. Agents imbued with artificial social …

Assessment methods of post-stroke gait: A scoping review of technology-driven approaches to gait characterization and analysis

DM Mohan, AH Khandoker, SA Wasti… - Frontiers in …, 2021 - frontiersin.org
Background: Gait dysfunction or impairment is considered one of the most common and
devastating physiological consequences of stroke, and achieving optimal gait is a key goal …

Towards best practice in explaining neural network decisions with LRP

M Kohlbrenner, A Bauer, S Nakajima… - … Joint Conference on …, 2020 - ieeexplore.ieee.org
Within the last decade, neural network based predictors have demonstrated impressive-and
at times superhuman-capabilities. This performance is often paid for with an intransparent …

[HTML][HTML] CLEVR-XAI: A benchmark dataset for the ground truth evaluation of neural network explanations

L Arras, A Osman, W Samek - Information Fusion, 2022 - Elsevier
The rise of deep learning in today's applications entailed an increasing need in explaining
the model's decisions beyond prediction performances in order to foster trust and …