Explaining deep neural networks and beyond: A review of methods and applications
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) …
sciences, there has been a growing demand for explainable artificial intelligence (XAI) …
Layer-wise relevance propagation: an overview
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 …
supported by meaningful patterns in the input data. A prerequisite is however for the model …
Unmasking Clever Hans predictors and assessing what machines really learn
Current learning machines have successfully solved hard application problems, reaching
high accuracy and displaying seemingly intelligent behavior. Here we apply recent …
high accuracy and displaying seemingly intelligent behavior. Here we apply recent …
Explainable artificial intelligence (xai) on timeseries data: A survey
Most of state of the art methods applied on time series consist of deep learning methods that
are too complex to be interpreted. This lack of interpretability is a major drawback, as several …
are too complex to be interpreted. This lack of interpretability is a major drawback, as several …
What clinicians want: contextualizing explainable machine learning for clinical end use
S Tonekaboni, S Joshi… - Machine learning …, 2019 - proceedings.mlr.press
Translating machine learning (ML) models effectively to clinical practice requires
establishing clinicians' trust. Explainability, or the ability of an ML model to justify its …
establishing clinicians' trust. Explainability, or the ability of an ML model to justify its …
[HTML][HTML] Explainable, trustworthy, and ethical machine learning for healthcare: A survey
With the advent of machine learning (ML) and deep learning (DL) empowered applications
for critical applications like healthcare, the questions about liability, trust, and interpretability …
for critical applications like healthcare, the questions about liability, trust, and interpretability …
A deep convolutional neural network for COVID-19 detection using chest X-rays
PRAS Bassi, R Attux - Research on Biomedical Engineering, 2021 - Springer
Purpose We present image classifiers based on Dense Convolutional Networks and transfer
learning to classify chest X-ray images according to three labels: COVID-19, pneumonia …
learning to classify chest X-ray images according to three labels: COVID-19, pneumonia …
Towards best practice in explaining neural network decisions with LRP
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 …
at times superhuman-capabilities. This performance is often paid for with an intransparent …
A spatial-temporal layer-wise relevance propagation method for improving interpretability and prediction accuracy of LSTM building energy prediction
G Li, F Li, C Xu, X Fang - Energy and Buildings, 2022 - Elsevier
At present, data-driven methods have achieved satisfactory results in building energy
consumption prediction, especially deep learning models such as long short-term memory …
consumption prediction, especially deep learning models such as long short-term memory …
When explanations lie: Why many modified bp attributions fail
Attribution methods aim to explain a neural network's prediction by highlighting the most
relevant image areas. A popular approach is to backpropagate (BP) a custom relevance …
relevant image areas. A popular approach is to backpropagate (BP) a custom relevance …