neural-networks

Reduced-Dimensional Neural Network Surrogate Construction and Calibration of the E3SM Land Model

Talk

Uncertainty Quantification in Neural Networks

Talk

Visualizing and Quantifying Uncertainty of Physics-aware Neural Networks

Talk

Analysis of Neural Networks as Random Dynamical Systems

In this report we present our findings and outcomes of the NNRDS (analysis of Neural Networks as Random Dynamical Systems) project. The work is largely motivated by the analogy of a large class of neural networks (NNs) with a discretized ordinary …

Quantifying Uncertainties in Residual Neural Networks and Neural ODEs

Talk

Configuration Space Integration for Adsorbate Partition Functions: The Effect of Anharmonicity on the Thermophysical Properties of CO–Pt(111) and CH3OH–Cu(111)

A method for computing anharmonic thermophysical properties for adsorbates on metal surfaces has been extended to include libration, or frustrated rotation. Classical phase space integration is used with Monte Carlo sampling of the configuration …

The Role of Stiffness in Training and Generalization of ResNets

Neural ordinary differential equations (NODEs) have recently regained popularity as large-depth limits of a large class of neural networks. In particular, residual neural networks (ResNets) are equivalent to an explicit Euler discretization of an …

Training and Generalization of Residual Neural Networks as Discrete Analogues of Neural ODEs

Talk

UQ and Model Error Estimation for Machine Learning Interatomic Potentials

Talk

Minima-preserving neural network (MPNN) for potential energy surface approximation

Talk