物理知情深度生成建模的变异推理的入门教程
Alex Glyn-Davies1, Arnaud Vadeboncoeur1, O Deniz Akyildiz2
1Department of Engineering, University of Cambridge, Cambridge, Cambridgeshire, UK.
变量推理 (VI) 为物理问题提供有效的贝叶斯推理,平衡准确性和可处理性. 本文介绍了使用深度学习的前向和反向问题的VI,强调不确定性量化.
科学领域:
- 计算物理 计算物理
- 贝叶斯的推理是贝叶斯的推理.
- 机器学习 机器学习
背景情况:
- 变量推理 (VI) 是用于近似贝叶斯推理的可扩展方法.
- 它平衡了不确定性量化准确性与计算可处理性.
- VI非常适合用于物理中的生成建模和反转任务.
研究的目的:
- 为基于物理的前向和反向问题提供VI的技术介绍.
- 通过深度学习指导读者实施VI.
- 审查和统一最近关于VI在物理学中的应用的文献.
主要方法:
- 根据物理模型量身定制的VI学习目标的推导.
- VI与深度学习框架的整合.
- 对物理推理中的VI灵活性现有文献的审查.
主要成果:
- 证明VI在基于物理问题的有效性.
- 突出物理模型结构在VI中的作用.
- 通过各种应用来展示VI的灵活性.
结论:
- VI 是物理中不确定性量化的一个强大的工具.
- 深度学习增强了对复杂问题的VI的实现.
- 这项工作统一并扩大了科学计算中VI的理解.
更多相关视频
06:20Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training
Published on: December 6, 2024
11:03An Analog Macroscopic Technique for Studying Molecular Hydrodynamic Processes in Dense Gases and Liquids
Published on: December 4, 2017
相关概念视频
Estimation of the Physical Quantities
Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
Force and Potential Energy in Three Dimensions
Modeling and Similitude
Three-Dimensional Force System
Curvilinear Motion: Rectangular Components
As the car advances, its position evolves over time. Quantifying the car's velocity involves computing the...
