对潜在能量表面的多忠实机器学习模型进行比较
Stephen M Goodlett1, Justin M Turney1, Henry F Schaefer1
1Center for Computational Quantum Chemistry, University of Georgia, Athens, Georgia 30602, USA.
The Journal of chemical physics
|July 26, 2023
概括
多忠实度建模结合了准确的数据和许多不太准确的数据,以获得更好的模型. 对于潜在能量表面, Δ-学习与神经网络提供了最实用和准确的结果.
科学领域:
- 计算化学的计算化学
- 机器学习 机器学习
- 数据融合数据融合
背景情况:
- 多忠实度建模集成了不同精度和大小的数据集.
- 它有利于利用计算化学数据建模潜在能量表面.
- 在有效地结合低保真度 (丰富,不太准确) 和高保真度 (稀缺,准确) 数据方面存在挑战.
研究的目的:
- 为了比较各种基于神经网络的多真实性建模方法的性能.
- 评估它们在建模潜在能量表面方面的有效性.
- 确定这个任务的最实用和最准确的方法.
主要方法:
- 实施和比较四种神经网络多忠实度方法:双, Δ-学习,重量转移和孟-卡尼亚达基斯网络.
- 训练和测试这些方法使用低保真度 (许多廉价的能源计算) 和高保真度 (更少准确的电子能量) 的数据集.
- 与具有相同培训数据的传统神经网络实现进行基准测试.
主要成果:
- 这四种多忠实神经网络方法都超过了传统的神经网络.
- 在经过测试的方法中,Δ-学习方法表现出卓越的实用性和准确性.
- 这项研究证实了多真实性建模对于潜在能量表面计算的优势.
结论:
- 基于神经网络的多真实性建模是一种强大的技术,可以提高模型的准确性和效率.
- Δ-学习方法作为一种非常有效和实用的方法,用于潜在能量表面建模.
- 这项工作为计算化学家和机器学习从业者提供了宝贵的见解.
相关概念视频
01:29Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
81
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
81
01:14Multicompartment Models: Overview
182
Multicompartment models are mathematical constructs that depict how drugs are distributed and eliminated within the body. They segment the body into several compartments, symbolizing various physiological or anatomical areas connected through drug transfer processes such as absorption, metabolism, distribution, and elimination.
These models offer a more comprehensive representation of drug behavior in the body than one-compartment models. They accommodate the complexity of drug distribution,...
These models offer a more comprehensive representation of drug behavior in the body than one-compartment models. They accommodate the complexity of drug distribution,...
182
02:00Molecular Models
38.6K
Physical models representing molecular architectures of chemical compounds play essential roles in understanding chemistry. The use of molecular models makes it easier to visualize the structures and shapes of atoms and molecules.
38.6K
01:16Potential-Energy Criterion for Equilibrium
574
Potential energy or potential function plays an essential role in determining the stability of a mechanical system. If a system is subjected to both gravitational and elastic forces, the potential function of the system can be expressed as the algebraic sum of gravitational and elastic potential energy. If the system is in equilibrium and is displaced by a small amount, then the work done on the system equals the negative of the change in the system's potential energy from the initial to...
574
02:27Predicting Molecular Geometry
34.5K
VSEPR Theory for Determination of Electron Pair Geometries
34.5K
01:26Pharmacokinetic Models: Comparison and Selection Criterion
109
Physiological and compartmental models are valuable tools used in studying biological systems. These models rely on differential equations to maintain mass balance within the system, ensuring an accurate representation of the dynamic processes at play.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
109