Related papers: Probabilistic neural network approach to determini…
This paper investigates the use of probabilistic neural networks (PNNs) to model aleatoric uncertainty, which refers to the inherent variability in the input-output relationships of a system, often characterized by unequal variance or…
A simple, fully connected neural network with a single hidden layer is used to estimate stellar masses for star-forming galaxies. The model is trained on broad-band photometry - from far-ultraviolet to mid-infrared wavelengths - generated…
High-precision radial-velocity techniques, which enabled the detection of extrasolar planets are now sensitive to relativistic effects in the data of spectroscopic binary stars (SBs). We show how these effects can be used to derive the…
Bayesian Neural Networks (BNNs) provide a tool to estimate the uncertainty of a neural network by considering a distribution over weights and sampling different models for each input. In this paper, we propose a method for uncertainty…
Modern nuclear data evaluation increasingly requires not only accurate scattering calculations, but also efficient methods for uncertainty quantification and parameter optimization, tasks that benefit from differentiable solvers amenable to…
Large surveys producing tera- and petabyte-scale databases require machine-learning and knowledge discovery methods to deal with the overwhelming quantity of data and the difficulties of extracting concise, meaningful information with…
Accurately measuring stellar ages and internal structures is challenging, but the inclusion of asteroseismic observables can substantially improve precision. However, the curse of dimensionality means this comes at a high computational cost…
How to effectively approximate real-valued parameters with binary codes plays a central role in neural network binarization. In this work, we reveal an important fact that binarizing different layers has a widely-varied effect on the…
Likelihood-free approaches are appealing for performing inference on complex dependence models, either because it is not possible to formulate a likelihood function, or its evaluation is very computationally costly. This is the case for…
Pulse profile modelling is a relativistic ray-tracing technique that can be used to infer masses, radii and geometric parameters of neutron stars. In a previous study, we looked at the performance of this technique when applied to…
Understanding the uncertainty of a neural network's (NN) predictions is essential for many purposes. The Bayesian framework provides a principled approach to this, however applying it to NNs is challenging due to large numbers of parameters…
Russell (1948) famously described eclipses as the "royal road" to stellar astrophysics. From photometric and spectroscopic observations it is possible to measure the masses and radii (to 1% or better!), and thus surface gravities and mean…
Exoplanet observations are currently analysed with Bayesian retrieval techniques. Due to the computational load of the models used, a compromise is needed between model complexity and computing time. Analysis of data from future facilities,…
Massive stars exhibit a perplexing mismatch between their inferred masses from different observational techniques, posing a significant challenge to our understanding of stellar evolution and structure. This discrepancy is believed to be…
It is difficult to discover pulsars via their gamma-ray emission because current instruments typically detect fewer than one photon per million rotations. This creates a significant computing challenge for isolated pulsars, where the…
Recent developments in computational power and machine learning techniques motivate their use in many different astrophysical research areas. Consequently, many machine learning models have been trained to classify exoplanet transit signals…
Eclipsing systems are essential objects for understanding the properties of stars and stellar systems. Eclipsing systems with pulsating components are furthermore advantageous because they provide accurate constraints on the component…
Deep neural networks can be roughly divided into deterministic neural networks and stochastic neural networks.The former is usually trained to achieve a mapping from input space to output space via maximum likelihood estimation for the…
Data-driven methods based on machine learning have the potential to accelerate computational analysis of atomic structures. In this context, reliable uncertainty estimates are important for assessing confidence in predictions and enabling…
Asteroseismology may in principle be used to detect unresolved stellar binary systems comprised of solar-type stars and/or red giants. This novel method relies on the detection of the presence of two solar-like oscillation spectra in the…