Crystal Structure Prediction Using a Self-Attention Neural Network and Semantic Segmentation DOI

Wuling Zhao,

Mingting Zhou,

Jialin Shao

et al.

Journal of Chemical Information and Modeling, Journal Year: 2025, Volume and Issue: unknown

Published: April 14, 2025

The development of new materials is a time-consuming and resource-intensive process. Deep learning has emerged as promising approach to accelerate this However, accurately predicting crystal structures using deep remains significant challenge due the complex, high-dimensional nature atomic interactions scarcity comprehensive training data that captures full diversity possible configurations. This work developed neural network model based on set comprising thousands crystallographic information files from existing structure databases. incorporates self-attention mechanism enhance prediction accuracy by extracting both local global features three-dimensional structures, treating atoms in each point sets. enables effective semantic segmentation accurate unit cell prediction. Experimental results demonstrate for cells containing up 500 atoms, achieves 89.78%.

Language: Английский

Leveraging LLaMA2 for improved document classification in English DOI Creative Commons
Xu Jia

PeerJ Computer Science, Journal Year: 2025, Volume and Issue: 11, P. e2740 - e2740

Published: Feb. 28, 2025

Document classification is an important component of natural language processing, with applications that include sentiment analysis, content recommendation, and information retrieval. This article investigates the potential Large Language Model Meta AI (LLaMA2), a cutting-edge model, to enhance document in English. Our experiments show LLaMA2 outperforms traditional methods, achieving higher precision recall values on WOS-5736 dataset. Additionally, we analyze interpretability LLaMA2's process reveal most pertinent features for categorization model's decision-making. These results emphasize advanced models outcomes provide more profound comprehension structures, thereby contributing advancement processing methodologies.

Language: Английский

Citations

0
Crystal Structure Prediction Using a Self-Attention Neural Network and Semantic Segmentation DOI

Wuling Zhao,

Mingting Zhou,

Jialin Shao

et al.

Journal of Chemical Information and Modeling, Journal Year: 2025, Volume and Issue: unknown

Published: April 14, 2025

The development of new materials is a time-consuming and resource-intensive process. Deep learning has emerged as promising approach to accelerate this However, accurately predicting crystal structures using deep remains significant challenge due the complex, high-dimensional nature atomic interactions scarcity comprehensive training data that captures full diversity possible configurations. This work developed neural network model based on set comprising thousands crystallographic information files from existing structure databases. incorporates self-attention mechanism enhance prediction accuracy by extracting both local global features three-dimensional structures, treating atoms in each point sets. enables effective semantic segmentation accurate unit cell prediction. Experimental results demonstrate for cells containing up 500 atoms, achieves 89.78%.

Language: Английский

Citations

0