中文
相关论文

相关论文: Bayesian neural networks for the probabilistic for…

200 篇论文

To advance the transparency of learning machines such as Deep Neural Networks (DNNs), the field of Explainable AI (XAI) was established to provide interpretations of DNNs' predictions. While different explanation techniques exist, a popular…

Artificial Neural Networks (ANNs) have been successfully used in various nuclear engineering applications, such as predicting reactor physics parameters within reasonable time and with a high level of accuracy. Despite this success, they…

机器学习 · 统计学 2023-03-24 Lesego E. Moloko , Pavel M. Bokov , Xu Wu , Kostadin N. Ivanov

Modern neural networks tend to be overconfident on unseen, noisy or incorrectly labelled data and do not produce meaningful uncertainty measures. Bayesian deep learning aims to address this shortcoming with variational approximations (such…

机器学习 · 统计学 2018-05-28 Nick Pawlowski , Andrew Brock , Matthew C. H. Lee , Martin Rajchl , Ben Glocker

Spiking Neural Networks (SNNs) are naturally suited for speech processing tasks due to their specific dynamics, which allows them to handle temporal data. However, the threshold-based generation of spikes in SNNs intuitively causes an…

机器学习 · 计算机科学 2026-04-13 Yesmine Abdennadher , Philip N. Garner

This paper investigates two prominent probabilistic neural modeling paradigms: Bayesian Neural Networks (BNNs) and Mixture Density Networks (MDNs) for uncertainty-aware nonlinear regression. While BNNs incorporate epistemic uncertainty by…

统计计算 · 统计学 2025-10-30 Riddhi Pratim Ghosh , Ian Barnett

Neural Networks (NNs) have provided state-of-the-art results for many challenging machine learning tasks such as detection, regression and classification across the domains of computer vision, speech recognition and natural language…

机器学习 · 统计学 2026-04-21 Ethan Goan , Clinton Fookes

Renewable sources of energy are the future due to the environmental problems caused by non-renewable sources to produce energy. The biggest issue with renewable energy sources is that the power produced by devices such as PV solar panels…

信号处理 · 电气工程与系统科学 2022-10-24 Rohaib Bhatti , Ali John Naqvi , Abdullah Tauqeer

Because of the global need to increase power production from renewable energy resources, developments in the online monitoring of the associated infrastructure is of interest to reduce operation and maintenance costs. However, challenges…

机器学习 · 计算机科学 2025-10-29 Simon M. Brealy , Lawrence A. Bull , Pauline Beltrando , Anders Sommer , Nikolaos Dervilis , Keith Worden

Bayesian neural networks (BNNs) have recently regained a significant amount of attention in the deep learning community due to the development of scalable approximate Bayesian inference techniques. There are several advantages of using a…

机器学习 · 统计学 2023-05-02 Aliaksandr Hubin , Geir Storvik

Climate change is one of the most concerning issues of this century. Emission from electric power generation is a crucial factor that drives the concern to the next level. Renewable energy sources are widespread and available globally,…

机器学习 · 计算机科学 2020-05-27 Md Amimul Ehsan , Amir Shahirinia , Nian Zhang , Timothy Oladunni

Deep neural networks have outperformed existing machine learning models in various molecular applications. In practical applications, it is still difficult to make confident decisions because of the uncertainty in predictions arisen from…

机器学习 · 计算机科学 2019-03-21 Seongok Ryu , Yongchan Kwon , Woo Youn Kim

For the retrieval of large-scale vegetation biophysical parameters, the inversion of radiative transfer models (RTMs) is the most commonly used approach. In recent years, Artificial Neural Network (ANN)-based methods have become the…

机器学习 · 计算机科学 2024-11-08 Dasheng Fan , Xihan Mu , Yongkang Lai , Donghui Xie , Guangjian Yan

Accurate marine wind forecasts are essential for safe navigation, ship routing, and energy operations, yet they remain challenging because observations over the ocean are sparse, heterogeneous, and temporally variable. We reformulate wind…

机器学习 · 计算机科学 2025-12-04 Matteo Peduto , Qidong Yang , Jonathan Giezendanner , Devis Tuia , Sherrie Wang

The mapping of ocean floor layers is a current challenge for the oil industry. Existing solution methods involve mapping through seismic methods and wave inversion, which are complex and computationally expensive. The introduction of…

机器学习 · 计算机科学 2024-12-10 Guilherme G. D. Fernandes , Vitor S. P. P. Oliveira , João P. I. Astolfo

Neural networks with binary weights are computation-efficient and hardware-friendly, but their training is challenging because it involves a discrete optimization problem. Surprisingly, ignoring the discrete nature of the problem and using…

机器学习 · 计算机科学 2020-08-19 Xiangming Meng , Roman Bachmann , Mohammad Emtiyaz Khan

The need for function estimation in label-limited settings is common in the natural sciences. At the same time, prior knowledge of function values is often available in these domains. For example, data-free biophysics-based models can be…

机器学习 · 计算机科学 2022-10-17 Hunter Nisonoff , Yixin Wang , Jennifer Listgarten

Neural networks (NN) have been recently applied together with evolutionary algorithms (EAs) to solve dynamic optimization problems. The applied NN estimates the position of the next optimum based on the previous time best solutions. After…

神经与进化计算 · 计算机科学 2020-02-03 Maryam Hasani-Shoreh , Renato Hermoza Aragonés , Frank Neumann

Neural Ordinary Differential Equations (N-ODEs) are a powerful building block for learning systems, which extend residual networks to a continuous-time dynamical system. We propose a Bayesian version of N-ODEs that enables well-calibrated…

机器学习 · 计算机科学 2020-02-19 Andreas Look , Melih Kandemir

Magnetotelluric (MT) inversion is a key technique in geophysics for imaging deep subsurface resistivity structures. However, the inherent ill-posedness and non-uniqueness of inverse problems make them challenging to solve. While supervised…

地球物理 · 物理学 2025-08-06 Dhruv Poddar , Rohan Sharma , Divakar Vashisth

Bayesian Neural Networks (BNN) have recently emerged in the Deep Learning world for dealing with uncertainty estimation in classification tasks, and are used in many application domains such as astrophysics, autonomous driving...BNN assume…

机器学习 · 计算机科学 2021-02-04 Claire Theobald , Frédéric Pennerath , Brieuc Conan-Guez , Miguel Couceiro , Amedeo Napoli