Bayesian neural networks harness the power of Bayesian inference which provides an
approach to neural learning that not only focuses on accuracy but also uncertainty …

Traditional approaches to develop 3D geological models employ a mix of quantitative and
qualitative scientific techniques, which do not fully provide quantification of uncertainty in the …

Bayesian inference provides a rigorous approach for neural learning with knowledge
representation via the posterior distribution that accounts for uncertainty quantification …

Cyclone track forecasting is a critical climate science problem involving time-series
prediction of cyclone location and intensity. Machine learning methods have shown much …

Although the use of deep learning and neural networks techniques are gaining popularity,
there remain a number of challenges when multiple sources of information and data need to …

Neuroevolution is a machine learning method for evolving neural networks parameters and
topology with a high degree of flexibility that makes them applicable to a wide range of …

Bayesian inference provides a methodology for parameter estimation and uncertainty
quantification in machine learning and deep learning methods. Variational inference and …

Deep learning models, such as convolutional neural networks, have long been applied to
image and multi-media tasks, particularly those with structured data. More recently, there …

Autoencoders gained popularity in the deep learning revolution given their ability to
compress data and provide dimensionality reduction. Although prominent deep learning …

At the start of its centennial year, AGU's surface process community revisited GK Gilbert's
legacy of landscape description and experimental models of surface processes, as well as …