Related papers: Temperature Optimization for Bayesian Deep Learnin…

Class imbalance has a detrimental effect on the predictive performance of most supervised learning algorithms as the imbalanced distribution can lead to a bias preferring the majority class. To solve this problem, we propose a Supervised…

We present Posterior Temperature Optimized Bayesian Inverse Models (POTOBIM), an unsupervised Bayesian approach to inverse problems in medical imaging using mean-field variational inference with a fully tempered posterior. Bayesian methods…

Background: In medical imaging, images are usually treated as deterministic, while their uncertainties are largely underexplored. Purpose: This work aims at using deep learning to efficiently estimate posterior distributions of imaging…

Since model bias and associated initialization shock are serious shortcomings that reduce prediction skills in state-of-the-art decadal climate prediction efforts, we pursue a complementary machine-learning-based approach to climate…

This study presents a machine learning approach to predict the Curie temperature in binary alloys, specifically focusing on the Fe-Pt, Fe-Ni, Fe-Pd, and Co-Pt compounds within a concentration range of 10 to 90 atomic percent. The optimal…

Thermal management in the hyper-scale cloud data centers is a critical problem. Increased host temperature creates hotspots which significantly increases cooling cost and affects reliability. Accurate prediction of host temperature is…

Conditional probability density functional theory has recently been used to derive the temperature dependence of the Perdew-Burke-Ernzerhof (PBE) generalized gradient approximation (GGA) for the exchange-correlation (XC) free energy. We…

Deep Learning (DL) has shown promise for downscaling global climate change projections under different approaches, including Perfect Prognosis (PP) and Regional Climate Model (RCM) emulation. Unlike emulators, PP downscaling models are…

Recently, there have been many works on the deep learning of statistical ensembles to determine the critical temperature of a possible phase transition. We analyze the detailed structure of an optimized deep learning machine and prove the…

Precise temperature measurements on systems of few ultracold atoms is of paramount importance in quantum technologies, but can be very resource-intensive. Here, we put forward an adaptive Bayesian framework that substantially boosts the…

Neural posterior estimation (NPE) and neural likelihood estimation (NLE) are machine learning approaches that provide accurate posterior, and likelihood, approximations in complex modeling scenarios, and in situations where conducting…

Much research in recent years has focused on using empirical machine learning approaches to extract useful insights on the structure-property relationships of superconductor material. Notably, these approaches are bringing extreme benefits…

The prediction reliability of neural networks is important in many applications. Specifically, in safety-critical domains, such as cancer prediction or autonomous driving, a reliable confidence of model's prediction is critical for the…

Weather forecasting centers currently rely on statistical postprocessing methods to minimize forecast error. This improves skill but can lead to predictions that violate physical principles or disregard dependencies between variables, which…

Cryopreservation is beset with the challenge of protocol alignment across a wide range of cell types and process variables. By taking a cross-sectional assessment of previously published cryopreservation data (sample means and standard…

A central idea of knowledge distillation is to expose relational structure embedded in the teacher's weights for the student to learn, which is often facilitated using a temperature parameter. Despite its widespread use, there remains…

Scientific machine learning has been successfully applied to inverse problems and PDE discovery in computational physics. One caveat concerning current methods is the need for large amounts of ("clean") data, in order to characterize the…

In this paper, we study the post-hoc calibration of modern neural networks, a problem that has drawn a lot of attention in recent years. Many calibration methods of varying complexity have been proposed for the task, but there is no…

Class probabilities predicted by most multiclass classifiers are uncalibrated, often tending towards over-confidence. With neural networks, calibration can be improved by temperature scaling, a method to learn a single corrective…

Simulating warm dense matter that undergoes a wide range of temperatures and densities is challenging. Predictive theoretical models, such as quantum-mechanics-based first-principles molecular dynamics (FPMD), require a huge amount of…