5 papers
Probabilistic Physics-Informed Neural Solvers for Woods-Saxon Parameter Identification: A Coupled Forward-Inverse Approach
Iraklis Spyrou, Christos Tsepas, Vaia Prassa +1
The Woods-Saxon mean-field approach offers a compact description of bound single-particle motion in finite nuclei, while physics-informed neural networks (PINNs) provide a differen…
An Explainable Physics-Informed Neural Frequency-Response Framework for Shunt-Parameter Identification in Semi-Active Piezoelectric Tuned Mass Dampers
Andreas Georgiou, Vasileios Gkatsis, Vasileios Sioros +3
This paper proposes a Physics-Informed Neural Frequency Response Framework for learning and interpreting the frequency-domain behavior of semi-active shunted piezoelectric tuned ma…
Towards trajectory-unsupervised physics-informed neural solvers for molecular dynamics
Petros Triantafyllos, Panagiotis Krokidas, Christoforos Rekatsinas
Molecular dynamics (MD) simulations are governed by explicit equations of motion, yet most neural approaches that accelerate or emulate MD rely on simulator-generated trajectories,…
Active Learning Guided Design Space Refinement for Scalable Multi-Objective Bayesian Optimization in Materials Discovery
Alexandros Ntagiantas, Panagiotis Tsilimidos, George Giannakopoulos +2
Advanced materials discovery increasingly relies on machine learning and Bayesian optimization to explore large discrete design spaces under limited evaluation budgets. However, co…
Frugal Bayesian Optimization: Scalable Surrogates for Data- and Resource-Limited Discovery
Panagiotis Krokidas, Christoforos Rekatsinas, Vassilis Sioros +3
Bayesian Optimization (BO) is widely adopted for data-efficient optimization in scientific and engineering applications, yet its computational cost is rarely evaluated alongside op…