相关实验视频
Updated: Sep 14, 2025

Surrogate Model Development for Digital Experiments in Welding
Published on: March 28, 2025
一个简单的近似贝叶斯推理神经替代物,用于随机培养网模型.
Bright Kwaku Manu1, Trevor Reckell2, Beckett Sterner3
1School of Computing and Augmented Intelligence Arizona State University, Tempe, 85281.
我们开发了一个神经替代模型,以估计在随机彼得里网 (SPN) 中的参数,即使缺少数据. 这种数据驱动的方法为复杂的系统提供了快速而准确的参数恢复.
科学领域:
- 计算生物学 计算生物学
- 系统生物学 系统生物学
- 机器学习 机器学习
背景情况:
- 随机 Petri 网 (SPN) 对于在流行病学和系统生物学等领域建模离散事件系统至关重要.
- 在SPN中对参数进行估计是很困难的,尤其是在共变量依赖率和缺失的概率的情况下.
研究的目的:
- 引入一个神经替代框架,用于在部分观察到的SPN中准确估计参数.
- 为了应对模拟系统中的挑战,在模拟系统中,明确的概率是不可用的,过渡率取决于共变量.
主要方法:
- 开发了一个使用1D卷积残余网络的神经替代框架.
- 该模型在吉尔斯皮模拟的SPN实现上进行了端到端的训练,学习如何从噪音轨迹中逆转系统动态.
- 蒙特卡洛脱落被用于推理过程中的不确定性量化.
主要成果:
- 替代模型准确地恢复了合成SPN的速率函数系数 (RMSE = 0.108),其中20%的事件缺失.
- 与传统的贝叶斯方法相比,神经替代方法的表现明显更快.
- 除了点估计,还提供了校准的不确定性边界.
结论:
- 数据驱动的,无概率的神经替代品使复杂的,部分观察的离散事件系统能够实现强大的实时参数恢复.
- 这一框架提高了SPN在需要从不完整数据中高效准确的参数估计的领域的适用性.
更多相关视频
10:50Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches
Published on: June 21, 2022
10:44Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
Published on: December 7, 2021
相关概念视频
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...
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
Neural Circuits
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation
On...
Model Approaches for Pharmacokinetic Data: Physiological Models
Propagation of Uncertainty from Random Error