Results 61 to 70 of about 6,698,922 (291)
Fast Graph Convolutional Recurrent Neural Networks [PDF]
This paper proposes a Fast Graph Convolutional Neural Network (FGRNN) architecture to predict sequences with an underlying graph structure. The proposed architecture addresses the limitations of the standard recurrent neural network (RNN), namely, vanishing and exploding gradients, causing numerical instabilities during training.
Sai Kiran Kadambari +1 more
openaire +3 more sources
Path integral based convolution and pooling for graph neural networks [PDF]
Graph neural networks (GNNs) extends the functionality of traditional neural networks to graph-structured data. Similar to CNNs, an optimized design of graph convolution and pooling is key to success.
Liò, P +14 more
core +1 more source
Intelligent prediction method of network performance based on graph neural network
There are some problems in the traditional network performance prediction technology, such as incomplete network state acquisition and poor accuracy of network performance evaluation.Combined with the characteristics of graph neural network learning and ...
Yijiang LI +5 more
doaj +2 more sources
Which brain hemisphere controls writing? This review synthesizes all five functional transcranial Doppler studies of writing (handwriting and typing) published to date in adults and children. Right‐handers show left‐hemispheric dominance for the linguistic component of writing (written word generation), whereas findings for left‐handers remain ...
Marietta Papadatou‐Pastou
wiley +1 more source
Compact & Capable: Harnessing Graph Neural Networks and Edge Convolution for Medical Image Classification [PDF]
Graph-based neural network models are gaining traction in the field of representation learning due to their ability to uncover latent topological relationships between entities that are otherwise challenging to identify.
Denny, Patrick +3 more
core +2 more sources
Ricci Curvature-Based Semi-Supervised Learning on an Attributed Network
In recent years, on the basis of drawing lessons from traditional neural network models, people have been paying more and more attention to the design of neural network architectures for processing graph structure data, which are called graph neural ...
Wei Wu, Guangmin Hu, Fucai Yu
doaj +1 more source
Neuromorphic plasticity in OECTs is governed by the post‐stimulus evolution of coupled ionic and electronic states. Semiconductor chemistry and morphology, electrolyte composition and interfaces, and device architecture regulate ion injection, transport, confinement, and release, shifting responses from rapidly relaxing STP to metastable memory and ...
Inho Lee +9 more
wiley +1 more source
Time-Evolving Graph Convolutional Recurrent Network for Traffic Prediction
Accurate traffic prediction is crucial to the construction of intelligent transportation systems. This task remains challenging because of the complicated and dynamic spatiotemporal dependency in traffic networks. While various graph-based spatiotemporal
Weimin Mai, Junxin Chen, Xiang Chen
doaj +1 more source
NeuroVisio SyncPatch integrates skin‐conformal electromyography (EMG) electrodes with camera‐tracked markers to jointly assess muscle activity and three‐dimensional knee kinematics during rehabilitation. Parallel feedback pathways provide real‐time kinematic guidance during movement and post‐trial neuromuscular feedback.
Bohyung Choi +11 more
wiley +1 more source
A Convolutional Neural Network into graph space [PDF]
Convolutional neural networks (CNNs), in a few decades, have outperformed the existing state of the art methods in classification context. However, in the way they were formalised, CNNs are bound to operate on euclidean spaces.
Raveaux, Romain +3 more
core +1 more source

