Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

39
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...
39

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same authorSame journal

Primitive Basic Amino Acids Promote Mineral-Catalyzed Electrochemical Reduction of H<sup>+</sup> and CO<sub>2</sub>.

The journal of physical chemistry. C, Nanomaterials and interfaces·2026
Same author

Mineral-facilitated aqueous synthesis of hydrogen cyanide from prebiotically abundant amino acids for chemical evolution.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Grand Challenges and Opportunities in Stimulated Dynamic and Resonant Catalysis.

ACS catalysis·2026
Same author

Sulfur-Stabilized High Entropy Oxysulfides Enable Efficient CC Bond Cleavage in Ethylene Glycol Electrooxidation for Sustainable Plastic Upcycling to Formate.

ChemSusChem·2026
Same author

Computational and Experimental Realization of Metal-Ion-Doped Orthorhombic Sn<sub>3</sub>O<sub>4</sub> for Visible-Light-Active Photocatalysis.

Journal of the American Chemical Society·2026
Same author

Enhanced Thermal- and Photostability of Trace Pyrazine-Incorporated Hydrogen Boride Nanosheets.

Small (Weinheim an der Bergstrasse, Germany)·2025

相关实验视频

Updated: Jun 2, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

366

提高机器学习潜力的成本效益战略,通过将来自多组件数据集的学习转移到 ænet-PyTorch 上.

An Niza El Aisnada1,2, Kajjana Boonpalit2,3, Robin van der Kruit2

  • 1Department of Materials Science and Engineering, School of Materials and Chemical Technology, Tokyo Institute of Technology, 2-12-1 Ookayama, Meguro-ku, Tokyo 152-8552, Japan.

The journal of physical chemistry. C, Nanomaterials and interfaces
|January 15, 2025
PubMed
概括
此摘要是机器生成的。

转移学习增强了催化剂-吸附剂模拟的机器学习潜力 (MLP),提高了准确性和稳定性,即使数据有限. 这种具有成本效益的方法可以为催化研究提供可靠的材料模拟.

更多相关视频

Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

947
Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
09:44

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

4.6K

相关实验视频

Last Updated: Jun 2, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

366
Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

947
Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
09:44

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

4.6K

科学领域:

  • 计算材料科学科学 计算材料科学
  • 催化剂是一种催化剂.
  • 机器学习 机器学习

背景情况:

  • 机器学习潜力 (MLP) 能够实现高效的材料模拟,但需要大量的初始数据.
  • 为催化剂-吸附剂系统构建大型参考数据库在计算上昂贵且具有挑战性.
  • 使用有限数据培训MLP可能会导致过度装配和减少实际适用性.

研究的目的:

  • 探索一个具有成本效益的转移学习策略,用于为催化剂-吸附剂系统开发准确的MLP.
  • 通过利用从公共数据库中预先训练的模型来调查有限的ab initio引用的使用.
  • 评估通过转移学习开发的MLPs的可通用性和稳定性.

主要方法:

  • 利用2020年开放催化剂项目 (OC20) 数据库进行MLP模型的预训练,使用 ænet-PyTorch 框架.
  • 对比了用于转移学习的OC20数据库中选择子集的不同策略.
  • 进行分子动力学模拟,以评估开发的MLP的稳定性和准确性.

主要成果:

  • 通过转移学习开发的MLP与从头开始训练的MLP相比,表现出更好的通用性和稳定性.
  • 转移学习显著提高了CuAu/H2O系统的MLP的准确性和稳定性,约有600个数据点.
  • 转移学习方法在CuAu/6H2O的分子动力学模拟中实现了高达250 ps的稳定和准确的预测,超过了没有转移学习的模型.

结论:

  • 转移学习为具有有限数据的催化剂-吸附剂系统构建准确的MLP提供了计算成本效益的方法.
  • 这一策略提高了MLP在分子动力学模拟中的稳定性和推断能力.
  • 拟议的方法促进了材料科学和催化学的更广泛应用,使得模拟更有效.