Results 81 to 90 of about 6,698,922 (291)

Organic Materials of Tomorrow: Horizons of Artificial Intelligence

open access: yesAdvanced Materials, EarlyView.
This review examines machine learning techniques accelerating the discovery of organic semiconductors by linking molecular structure to properties. Key methods include graph neural networks, generative models, and active learning. Applications to organic photovoltaics demonstrate practical impact.
Harold Mena   +3 more
wiley   +1 more source

Graph Convolutional Neural Networks based on Quantum Vertex Saliency [PDF]

open access: yes, 2019
This paper proposes a new Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes.
Cheng, Jian   +5 more
core   +1 more source

Multimodal Engagement Assessment in Children During Invented Story Paradigm With a Social Robot

open access: yesAdvanced Robotics Research, EarlyView.
A multimodal framework is proposed to assess children's engagement during storytelling interactions with a social robot. Gaze, physiological, and behavioral data are combined and validated against observer ratings. An automated gaze‐labeling strategy is introduced, and supervised classifiers achieve high accuracy. The study supports scalable engagement
Laura Fiorini   +7 more
wiley   +1 more source

Low-Rank Matrix Completion Using Graph Neural Network

open access: yes, 2020
In this paper, we propose the graph neural network (GNN)-based matrix completion technique to reconstruct the desired low-rank matrix by exploiting the underlying graph structure of the matrix.
Luong Trung Nguyen, Shim, Byonghyo
core   +1 more source

Building Attention and Edge Convolution Neural Networks for Bioactivity and Physical-Chemical Property Prediction [PDF]

open access: yes, 2019
We introduce Attention and Edge Memory schemes to the existing Message Passing Neural Network framework for graph convolution, and benchmark our approaches against eight different physical-chemical and bioactivity datasets from the literature.
Michael, Withnall   +3 more
core   +2 more sources

Forecasting Retweet Count during Elections Using Graph Convolution Neural Networks [PDF]

open access: yes, 2018
A retweet refers to sharing a tweet posted by another user on Twitter and is a primary way information spreads on the Twitter network. Political parties use Twitter extensively as a part of their campaign to promote their presence, announce their ...
Vijayan, Raghavendran
core   +2 more sources

Gated Graph Convolutional Recurrent Neural Networks [PDF]

open access: yes2019 27th European Signal Processing Conference (EUSIPCO), 2019
Graph processes model a number of important problems such as identifying the epicenter of an earthquake or predicting weather. In this paper, we propose a Graph Convolutional Recurrent Neural Network (GCRNN) architecture specifically tailored to deal with these problems.
Luana Ruiz   +2 more
openaire   +3 more sources

Backpropagation Through Soft Body: Investigating Information Processing in Brain–Body Coupling Systems

open access: yesAdvanced Robotics Research, EarlyView.
This study explores how information processing is distributed between brains and bodies through a codesign approach. Using the “backpropagation through soft body” framework, brain–body coupling agents are developed and analyzed across several tasks in which output is generated through the agents’ physical dynamics.
Hiroki Tomioka   +3 more
wiley   +1 more source

Processing of Incomplete Images by (Graph) Convolutional Neural Networks [PDF]

open access: yes, 2020
We investigate the problem of training neural networks from incomplete images without replacing missing values. For this purpose, we first represent an image as a graph, in which missing pixels are entirely ignored. The graph image representation is processed using a spatial graph convolutional network (SGCN) -- a type of graph convolutional networks ...
Tomasz Danel   +4 more
openaire   +5 more sources

Data‐Driven Bulldozer Blade Control for Autonomous Terrain Leveling

open access: yesAdvanced Robotics Research, EarlyView.
A simulation‐driven framework for autonomous bulldozer leveling is presented, combining high‐fidelity terramechanics simulation with a neural‐network‐based reduced‐order model. Gradient‐based optimization enables efficient, low‐level blade control that balances leveling quality and operation time.
Harry Zhang   +5 more
wiley   +1 more source

Home - About - Disclaimer - Privacy