Towards neural Earth system modelling by integrating artificial intelligence in Earth system science

C Irrgang, N Boers, M Sonnewald, EA Barnes… - Nature Machine …, 2021 - nature.com
Earth system models (ESMs) are our main tools for quantifying the physical state of the Earth
and predicting how it might change in the future under ongoing anthropogenic forcing. In …

Reassessing hierarchical correspondences between brain and deep networks through direct interface

NJ Sexton, BC Love - Science advances, 2022 - science.org
Functional correspondences between deep convolutional neural networks (DCNNs) and the
mammalian visual system support a hierarchical account in which successive stages of …

An empirical comparison of deep learning explainability approaches for EEG using simulated ground truth

A Sujatha Ravindran, J Contreras-Vidal - Scientific Reports, 2023 - nature.com
Recent advancements in machine learning and deep learning (DL) based neural decoders
have significantly improved decoding capabilities using scalp electroencephalography …

Two dimensions of opacity and the deep learning predicament

FJ Boge - Minds and Machines, 2022 - Springer
Deep neural networks (DNNs) have become increasingly successful in applications from
biology to cosmology to social science. Trained DNNs, moreover, correspond to models that …

Beyond generalization: a theory of robustness in machine learning

T Freiesleben, T Grote - Synthese, 2023 - Springer
The term robustness is ubiquitous in modern Machine Learning (ML). However, its meaning
varies depending on context and community. Researchers either focus on narrow technical …

On the philosophy of unsupervised learning

DS Watson - Philosophy & Technology, 2023 - Springer
Unsupervised learning algorithms are widely used for many important statistical tasks with
numerous applications in science and industry. Yet despite their prevalence, they have …

Adversarial attacks on image generation with made-up words

R Millière - arXiv preprint arXiv:2208.04135, 2022 - arxiv.org
Text-guided image generation models can be prompted to generate images using nonce
words adversarially designed to robustly evoke specific visual concepts. Two approaches for …

Corner case generation and analysis for safety assessment of autonomous vehicles

H Sun, S Feng, X Yan, HX Liu - Transportation research …, 2021 - journals.sagepub.com
Testing and evaluation is a crucial step in the development and deployment of connected
and automated vehicles (CAVs). To comprehensively evaluate the performance of CAVs, it …

Dear XAI community, we need to talk! Fundamental misconceptions in current XAI research

T Freiesleben, G König - World Conference on Explainable Artificial …, 2023 - Springer
Despite progress in the field, significant parts of current XAI research are still not on solid
conceptual, ethical, or methodological grounds. Unfortunately, these unfounded parts are …

Adversarial safety-critical scenario generation using naturalistic human driving priors

K Hao, W Cui, Y Luo, L Xie, Y Bai… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
Evaluating the decision-making system is indispensable in developing autonomous
vehicles, while realistic and challenging safety-critical test scenarios play a crucial role …