The mathematics behind artificial intelligence (AI) and machine learning (ML) rely on linear algebra, calculus, probability, ...

The dual-channel graph convolutional neural networks based on hybrid features jointly model the different features of networks, so that the features can learn each other and improve the performance of ...

Turing's 1950 paper didn't just pose the profound question, "Can machines think?". It ignited a quest to build AI technology ...

Existing research has focused on traditional graph neural networks, which use predefined graphs ... Then we propose a Decoupled Adaptive Graph Convolution Attention Network for Traffic Forecasting ...

The emergence of deep learning has not only brought great changes in the field of image recognition, but also achieved excellent node classification performance in graph neural networks. However, the ...

starting from traditional Convolutional Neural Networks (CNNs) to Vision Transformers and MLP-Mixers that were more recently introduced to represent images as sequences. Most recently, Vision Graph ...

cGCN on the graph-represented data can be extended to fMRI data ... Lebo, et al. "Application of convolutional recurrent neural network for individual recognition based on resting state fmri data." ...

we propose a Spatio-Temporal Multi-Graphs Convolutional Network (STMGCN), which collects information about the social interactions of pedestrians in a crowd by focusing on extracting the largest ...