Leveraging Machine Learning Potentials for In-Situ Searching of Active sites in Heterogeneous Catalysis

Precision Chemistry, Journal Year: 2024, Volume and Issue: 2(11), P. 570 - 586

Published: Sept. 11, 2024

This Perspective explores the integration of machine learning potentials (MLPs) in research heterogeneous catalysis, focusing on their role identifying

Language: Английский

Structural Optimization of Causal Driven Model Based on Bayesian Network in High-dimensional Data Classification

Applied Mathematics and Nonlinear Sciences, Journal Year: 2025, Volume and Issue: 10(1)

Published: Jan. 1, 2025

Abstract The Bayesian network (BN) model, as a big data graph model that integrates causal inference and probabilistic representation, has received widespread attention research in both academia industry. However, with the advent of era, traditional BN structure learning algorithms have encountered unprecedented challenges processing high-dimensional data, mainly manifested sharp increase computational complexity difficulty achieving ideal accuracy requirements within an acceptable time range, which greatly limits their breadth depth practical applications. In response to this bottleneck problem, article innovatively proposes new approach combines width theory BN, referred Broad Neural Network (Broad-BNN). This effectively reduces dimensionality original by introducing feature mapping layer gradually expanding it, while non-linear transformation information effective extraction. experimental results show proposed paper achieved significant performance improvement classification problems, not only accelerating training speed but also significantly improving accuracy, providing perspective solution for solving difficulties processing.

Language: Английский

Editorial: special topic on computation-assisted materials screening and design

Science China Materials, Journal Year: 2024, Volume and Issue: 67(4), P. 1011 - 1013

Published: March 26, 2024

Language: Английский