Results 101 to 110 of about 4,469 (193)
Stable and Fast Deep Mutual Information Maximization Based on Wasserstein Distance. [PDF]
Entropy (Basel), 2023 He X, Peng C, Wang L, Tan W, Wang Z.
europepmc +1 more source
Expert Systems, Volume 43, Issue 9, September 2026.ABSTRACT Evaluating synthetic data produced by generative models remains a critical challenge in sensitive domains such as healthcare and finance. Ensuring that such data is ‘faithful’ to real data is essential for downstream applications and decision‐making, including regulatory compliance. This paper introduces an AI‐powered interactive visual system—
Liqun Liu +5 more
wiley +1 more source
Advanced Intelligent Discovery, Volume 2, Issue 4, August 2026.We investigate MACE‐MP‐0 and M3GNet, two general‐purpose machine learning potentials, in materials discovery and find that both generally yield reliable predictions. At the same time, both potentials show a bias towards overstabilizing high energy metastable states. We deduce a metric to quantify when these potentials are safe to use.
Konstantin S. Jakob +2 more
wiley +1 more source
Towards Analysis of Covariance Descriptors via Bures–Wasserstein Distance
MathematicsA brain–computer interface (BCI) provides a direct communication pathway between the human brain and external devices, enabling users to control them through thought.
Huajun Huang +4 more
doaj +1 more source
Distance-Based Tree-Sliced Wasserstein Distance
CoRRTo overcome computational challenges of Optimal Transport (OT), several variants of Sliced Wasserstein (SW) has been developed in the literature. These approaches exploit the closed-form expression of the univariate OT by projecting measures onto (one-dimensional) lines.
Hoang V. Tran +5 more
openaire +3 more sources
A Data‐Driven Closed‐Loop Control Approach to Drive Neural State Transitions for Mechanistic Insight
Human Brain Mapping, Volume 47, Issue 11, 01 August 2026.The study introduces a data‐driven framework combining dynamical systems reconstruction and closed‐loop control to analyze brain‐state transitions in remitted depression. Using fMRI data, we show that these individuals more easily enter but struggle to exit sad mood states, revealing altered connectivity and potential neuromodulation targets for ...
Niklas Emonds +8 more
wiley +1 more source
MathematicsWhat if machines could seamlessly translate between the visual richness of images and the semantic depth of language with mathematical precision? This paper presents a theoretical and empirical analysis of five novel cross-modal Wasserstein adversarial ...
Joseph Tafataona Mtetwa +2 more
doaj +1 more source
Conditional Generative Modeling for Enhanced Credit Risk Management in Supply Chain Finance
Naval Research Logistics (NRL), Volume 73, Issue 5, Page 719-742, August 2026.ABSTRACT The rapid expansion of cross‐border e‐commerce (CBEC) has created significant opportunities for small‐ and medium‐sized sellers, yet financing remains a critical challenge due to their limited credit histories. Third‐party logistics (3PL)‐led supply chain finance (SCF) has emerged as a promising solution, leveraging in‐transit inventory as ...
Qingkai Zhang, L. Jeff Hong, Houmin Yan
wiley +1 more source
Gradient‐Free Online Learning of Subgrid‐Scale Dynamics With Neural Emulators
Journal of Advances in Modeling Earth Systems, Volume 18, Issue 8, August 2026.Abstract In this paper, we propose a generic algorithm to train machine learning‐based subgrid parametrizations online, that is, with a posteriori loss functions, but for non‐differentiable numerical solvers. The proposed approach leverages a neural emulator to approximate the reduced state‐space solver, which is then used to allow gradient propagation
H. Frezat +3 more
wiley +1 more source
Identifying disease-related microbes based on multi-scale variational graph autoencoder embedding Wasserstein distance. [PDF]
BMC Biol, 2023 Zhu H, Hao H, Yu L.
europepmc +1 more source