A self-explainable operator learning method reformulates operators as decomposable integral equations to reveal spatial input contributions to predictions in blood flow and aerodynamics problems.
Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
With the availability of large databases and recent improvements in deep learning methodology, the performance of AI systems is reaching or even exceeding the human level on an increasing number of complex tasks. Impressive examples of this development can be found in domains such as image classification, sentiment analysis, speech understanding or strategic game playing. However, because of their nested non-linear structure, these highly successful machine learning and artificial intelligence models are usually applied in a black box manner, i.e., no information is provided about what exactly makes them arrive at their predictions. Since this lack of transparency can be a major drawback, e.g., in medical applications, the development of methods for visualizing, explaining and interpreting deep learning models has recently attracted increasing attention. This paper summarizes recent developments in this field and makes a plea for more interpretability in artificial intelligence. Furthermore, it presents two approaches to explaining predictions of deep learning models, one method which computes the sensitivity of the prediction with respect to changes in the input and one approach which meaningfully decomposes the decision in terms of the input variables. These methods are evaluated on three classification tasks.
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative citing papers
Introduces a unified evaluation framework for XAI using five principled metrics and the PGCA method that fuses grid perturbation with Grad-CAM++ , reporting top scores in fidelity, interpretability and fairness on ResNet-50 models across five image domains.
SeisDiff-intp is a prompt-conditioned flow matching model that unifies multiple seismic interpretation tasks and generates realistic synthetic training data for complex subsurface features.
A Post-Recurrent Module added to RNNs yields 9% better P300 classification while identifying key spatio-temporal EEG patterns that match established neuroscience descriptions of the P300 wave.
Lightweight deep learning models perform comparably to larger ones for malaria detection, but explainability techniques degrade under image corruption even when predictions remain accurate.
Proposes an AI-augmented interactive system with built-in model interpretability to assist RECIST-based assessment of liver metastases.
citing papers explorer
-
Explainability of Recurrent Neural Networks for Enhancing P300-based Brain-Computer Interfaces
A Post-Recurrent Module added to RNNs yields 9% better P300 classification while identifying key spatio-temporal EEG patterns that match established neuroscience descriptions of the P300 wave.