Results 111 to 120 of about 1,708,308 (346)

The Laplacian spectrum of neural networks

Frontiers in Computational Neuroscience, 2014
The brain is a complex network of neural interactions, both at the microscopic and macroscopic level. Graph theory is well suited to examine the global network architecture of these neural networks.
Siemon ede Lange, Marcel ede Reus, Martijn eVan Den Heuvel   +2 more
doaj   +1 more source

Attention-Aware Heterogeneous Graph Neural Network

Big Data Mining and Analytics, 2021
As a powerful tool for elucidating the embedding representation of graph-structured data, Graph Neural Networks (GNNs), which are a series of powerful tools built on homogeneous networks, have been widely used in various data mining tasks.
Jintao Zhang, Quan Xu
doaj   +1 more source

Schatten Graph Neural Networks

IEEE Access, 2022
Graph Neural Networks (GNNs) have been intensively studied in recent years because of their promising performance over graph-structural data and have provided assistance in many fields. Recalling recent works on graph neural networks, we found that imposing graph smoothing via Frobenius norm was proven to be effective in the architecture of graph ...
Youfa Liu, Yongyong Chen, Guo Chen, Jiawei Zhang   +3 more
openaire   +2 more sources

Diffusion Spectrum Imaging Maps Early Axonal Loss and a Unique Progressive Signal in Neuronal Intranuclear Inclusion Disease

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objective To delineate specific in vivo white matter pathology in neuronal intranuclear inclusion disease (NIID) using diffusion spectrum imaging (DSI) and define its clinical relevance. Methods DSI was performed on 42 NIID patients and 38 matched controls.
Kaiyan Jiang, Yixiu Pei, Xiaobao Hu, Ying Xiong, Fang Wang, Yanyan Yu, Min Zhu, Dandan Tan, Meihong Zhou, Daojun Hong, Fuqing Zhou   +10 more
wiley   +1 more source

Neural network features distinguish chemosensory stimuli in Caenorhabditis elegans.

PLoS Computational Biology, 2021
Nervous systems extract and process information from the environment to alter animal behavior and physiology. Despite progress in understanding how different stimuli are represented by changes in neuronal activity, less is known about how they affect ...
Javier J How, Saket Navlakha, Sreekanth H Chalasani   +2 more
doaj   +1 more source

Degree-Aware Graph Neural Network Quantization

Entropy, 2023
In this paper, we investigate the problem of graph neural network quantization. Despite the great success on convolutional neural networks, directly applying current network quantization approaches to graph neural networks faces two challenges.
Ziqin Fan, Xi Jin
doaj   +1 more source

A Survey on Graph Neural Networks

IEEE Access
Graph Neural Networks (GNNs) have emerged as a fundamental class of models for analyzing graph-structured data, with broad applications spanning social networks, computational neuroscience, and intelligent transportation systems. In contrast to Euclidean data, graphs pose distinctive challenges due to their irregular topology, permutation invariance ...
Xinyang Zhang, Shengrong Li, Haoran Li 0024, Peiliang Gong, Jiahua Shi, Jun Shen 0001, Chunwei Tian, Daoqiang Zhang, Qi Zhu 0001   +8 more
openaire   +3 more sources

Graph Structure of Neural Networks

CoRR, 2020
Neural networks are often represented as graphs of connections between neurons. However, despite their wide use, there is currently little understanding of the relationship between the graph structure of the neural network and its predictive performance.
Jiaxuan You, Jure Leskovec, Kaiming He, Saining Xie   +3 more
openaire   +3 more sources

Structure–Function Decoupling of the Sensorimotor and Default Mode Networks in Black Americans With MS

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Background and Objectives Multiple sclerosis (MS) exhibits racially disparate rates of disease progression. Black people with MS (B‐PwMS) experience a more severe disease course than non‐Hispanic White people with MS (NHW‐PwMS). Here we investigated structural and functional connectivity as well as structure–function decoupling in the ...
Emilio Cipriano, Giacomo Boffa, Maria Petracca, Marta Ponzano, Nicole Graziano, Claire Wigley, Claire Riley, Jonathan Howard, Pietro Bontempi, Sylvia Klineova, Fred Lublin, Matilde Inglese   +11 more
wiley   +1 more source

Hierarchical Graph Neural Networks

CoRR, 2021
Over the recent years, Graph Neural Networks have become increasingly popular in network analytic and beyond. With that, their architecture noticeable diverges from the classical multi-layered hierarchical organization of the traditional neural networks.
openaire   +2 more sources