Shapley values for feature selection: The good, the bad, and the axioms
The Shapley value has become popular in the Explainable AI (XAI) literature, thanks, to a
large extent, to a solid theoretical foundation, including four “favourable and fair” axioms for …
large extent, to a solid theoretical foundation, including four “favourable and fair” axioms for …
[HTML][HTML] Explainable machine learning for project management control
Project control is a crucial phase within project management aimed at ensuring—in an
integrated manner—that the project objectives are met according to plan. Earned Value …
integrated manner—that the project objectives are met according to plan. Earned Value …
AggMapNet: enhanced and explainable low-sample omics deep learning with feature-aggregated multi-channel networks
Omics-based biomedical learning frequently relies on data of high-dimensions (up to
thousands) and low-sample sizes (dozens to hundreds), which challenges efficient deep …
thousands) and low-sample sizes (dozens to hundreds), which challenges efficient deep …
Inferring feature importance with uncertainties with application to large genotype data
Estimating feature importance, which is the contribution of a prediction or several predictions
due to a feature, is an essential aspect of explaining data-based models. Besides explaining …
due to a feature, is an essential aspect of explaining data-based models. Besides explaining …
Risk–Reward Share Allocation under Different Integrated Project Delivery Relational Structures: A Monte-Carlo Simulation and Cooperative Game Theoretic Solutions …
Sharing of risks and rewards is considered to be one of the key benefits and principles of
integrated project delivery (IPD). Despite its importance, risk–reward strategies are not …
integrated project delivery (IPD). Despite its importance, risk–reward strategies are not …
Beyond cuts in small signal scenarios: Enhanced sneutrino detectability using machine learning
D Alvestad, N Fomin, J Kersten, S Maeland… - The European Physical …, 2023 - Springer
We investigate enhancing the sensitivity of new physics searches at the LHC by machine
learning in the case of background dominance and a high degree of overlap between the …
learning in the case of background dominance and a high degree of overlap between the …
Towards interpreting ML-based automated malware detection models: A survey
Y Lin, X Chang - arXiv preprint arXiv:2101.06232, 2021 - arxiv.org
Malware is being increasingly threatening and malware detectors based on traditional
signature-based analysis are no longer suitable for current malware detection. Recently, the …
signature-based analysis are no longer suitable for current malware detection. Recently, the …
[HTML][HTML] Machine learning investigation of high-k metal gate processes for dynamic random access memory peripheral transistor
N Kwon, JH Bang, WJ Sung, JH Han, D Lee, I Jung… - APL Materials, 2024 - pubs.aip.org
Dynamic random access memory (DRAM) plays a crucial role as a memory device in
modern computing, and the high-k/metal gate (HKMG) process is essential for enhancing …
modern computing, and the high-k/metal gate (HKMG) process is essential for enhancing …
SARGDV: Efficient identification of groundwater-dependent vegetation using synthetic aperture radar
Groundwater depletion impacts the sustainability of numerous groundwater-dependent
vegetation (GDV) globally, placing significant stress on their capacity to provide …
vegetation (GDV) globally, placing significant stress on their capacity to provide …
Shapley Value for Shortest Path Routing in Dynamic Networks
A Masimli - 2023 - preprints.org
Transportation is a crucial component of supply chain management, responsible for
delivering goods and services to customers. This paper explores the application of game …
delivering goods and services to customers. This paper explores the application of game …