IEEE

Decoupled Dynamic Spatial–Temporal Graph Neural Network for Sea Surface Temperature Prediction

Abstract: Accurate sea surface temperature (SST) prediction is essential for advancing the understanding of marine ecosystems and global climate dynamics. SST variations arise from a dynamic interplay ...
eLife

Dynamic brain states during encoding and their post-encoding reinstatement predicts episodic memory in children

This study uses a Bayesian framework to characterize latent brain state dynamics associated with memory encoding and performance in children, as measured with functional magnetic resonance imaging.
Scientific Research Publishing

An Empirical Study Based on Big Data Analysis to Analyze Social Media Group Sentiment and Its Impact on Consumer Psychology ()

As social media becomes the core domain of information interaction in the era of big data, the emotional information contained in the vast amount of user-generated content provides an unprecedented ...
Techzine Europe

Qwen3.5 aims to position Alibaba alongside GPT and Claude

Alibaba is taking a step forward in developing open-source AI models with the introduction of Qwen3.5. The company claims ...
EurekAlert!

PolyU develops novel AI graph neural network models to unravel interdisciplinary complexities in image recognition and neuroscience

As an emerging technology in the field of artificial intelligence (AI), graph neural networks (GNNs) are deep learning models designed to process graph-structured data. Currently, GNNs are effective ...
IEEE

RandomViG: Random Vision Graph Neural Network for Image Classification

Abstract: Vision Graph Neural Network (ViG) is the first graph neural network model capable of directly processing image data. The community primarily focuses on the model structures to improve ViG’s ...
techxplore

New graph attention network models higher-order relationships in complex graph data

As an emerging technology in the field of artificial intelligence (AI), graph neural networks (GNNs) are deep learning models designed to process graph-structured data. Currently, GNNs are effective ...
Scientific Research Publishing

Picton, P. (1994) What Is a Neural Network? In: Picton, P., Ed., Introduction to Neural Networks, Macmillan Education, 1-12.

摘要: Machine learning (ML) has become an increasingly central component of high-energy physics (HEP), providing computational frameworks to address the growing complexity of theoretical calculations ...
C&EN

SFTGNN: An Efficient Spherical Fourier Transform-Enhanced Graph Neural Network for High-Accuracy Crystal Property Prediction

The prediction of the properties of crystal materials has always been a core issue in materials science and solid-state physics. With the rapid development of computer simulation techniques and ...
C&EN

GGCRB: A Graph Neural Network Approach for Predicting CircRNA–RBP Interactions Using Structural and Sequence Features

Creative Commons (CC): This is a Creative Commons license. Attribution (BY): Credit must be given to the creator. The interaction between circular RNAs (circRNAs) and RNA-binding proteins (RBPs) plays ...
EurekAlert!

Real-time, large-scale graph neural network inference through BingoCGN

BingoCGN employs cross-partition message quantization to summarize inter-partition message flow, which eliminates the need for irregular off-chip memory access and utilizes a fine-grained structured ...