Results 121 to 130 of about 84,208 (297)

Link Performance Prediction of Power Fiber Optic Communication System Based on Attention Mechanism and Convolutional Neural Network Fusion

Electrica
In order to enhance the multi-objective optimization capability of power communication transmission networks, the author proposes an optimization method that integrates improved graph neural networks (GNNs) and genetic algorithms (GAs).
Yong Zhang, Yan Liu, Chunying Wang, Jiaojiao Dong   +3 more
doaj   +1 more source

Joint Entity-Relation Extraction via Improved Graph Attention Networks

, 2020
Joint named entity recognition and relation extraction is an essential natural language processing task that aims to identify entities and extract the corresponding relations in an end-to-end manner. At present, compared with the named entity recognition
Qinghan Lai, Zihan Zhou, Song Liu
core   +1 more source

All‐in‐One Analog AI Hardware: On‐Chip Training and Inference with Conductive‐Metal‐Oxide/HfOx ReRAM Devices

Advanced Functional Materials, EarlyView.
An all‐in‐one analog AI accelerator is presented, enabling on‐chip training, weight retention, and long‐term inference acceleration. It leverages a BEOL‐integrated CMO/HfOx ReRAM array with low‐voltage operation (<1.5 V), multi‐bit capability over 32 states, low programming noise (10 nS), and near‐ideal weight transfer.
Donato Francesco Falcone, Victoria Clerico, Wooseok Choi, Tommaso Stecconi, Folkert Horst, Laura Bégon‐Lours, Matteo Galetta, Antonio La Porta, Nikhil Garg, Fabien Alibart, Bert Jan Offrein, Valeria Bragaglia   +11 more
wiley   +1 more source

GTAT: empowering graph neural networks with cross attention

Scientific Reports
Graph Neural Networks (GNNs) serve as a powerful framework for representation learning on graph-structured data, capturing the information of nodes by recursively aggregating and transforming the neighboring nodes’ representations.
Jiahao Shen, Qura Tul Ain, Yaohua Liu, Banqing Liang, Xiaoli Qiang, Zheng Kou   +5 more
doaj   +1 more source

Contrastive Graph Similarity Networks

Graph similarity learning is a significant and fundamental issue in the theory and analysis of graphs, which has been applied in a variety of fields, including object tracking, recommender systems, similarity search, and so on.
Li, Fuyi, Jin, D., Zheng, Yizhen, Jin, Di, Li, F., Pan, S., Pan, Shirui, Qiao, Yongliang, Zheng, Y., Wang, Luzhi, Qiao, Y., Wang, L.   +11 more
core   +1 more source

IN4MER Biomaterial Ink: A Phosphorescent Biosensing Biomaterial Ink for Multiple Analytes (Glucose, Lactate, Oxygen) Measurements and Temperature Sensing Applications

Advanced Functional Materials, EarlyView.
Multianalyte, real‐time monitoring of bioprinted scaffolds remains challenging. Phosphorescence‐lifetime–based, optically responsive microparticles are embedded in diverse printable hydrogels (κ‐carrageenan, GelMA, PEGDA) to form biomaterial inks that report oxygen, glucose, lactate, and temperature.
Waqas Saleem, David Chimene, Berkley P. White, Kaivalya A. Deo, Jeremy L. Thomas, Nithin Chidambara, Cole Mandrona, Kirsten Landsgaard, Brian Ko, Roland Kaunas, Akhilesh K. Gaharwar, Michael J. McShane   +11 more
wiley   +1 more source

Speckle‐Engineered Upconversion Amplification in Nanoemulsion‐Templated Hydrogel Microdomes

Advanced Functional Materials, EarlyView.
Nanoemulsion‐confined PEGDA microdomes generate speckle‐like excitation fields that strongly amplify upconversion luminescence upon dehydration, enabling filter‐free visible readout with reversible on–off switching. DMD‐based lithography yields scalable, shape‐programmable arrays for moisture‐responsive displays and optical encryption.
Chaeyeong Ryu, Byungcheon Yoo, Seunghun Lee, Hyungyo Jeong, Sanggyun Jeong, Heesu Cho, Jongwon Oh, Dahye Baek, Jongkyu Kim, Yubin Lee, Eunsu Gu, Dong‐Hwan Kim, Jung‐Hoon Park, Jiseok Lee   +13 more
wiley   +1 more source

Efficient Graph Generation with Graph Recurrent Attention Networks

CoRR, 2019
We propose a new family of efficient and expressive deep generative models of graphs, called Graph Recurrent Attention Networks (GRANs). Our model generates graphs one block of nodes and associated edges at a time. The block size and sampling stride allow us to trade off sample quality for efficiency.
Renjie Liao 0001, Yujia Li 0001, Yang Song 0011, Shenlong Wang, Charlie Nash, William L. Hamilton, David Duvenaud, Raquel Urtasun, Richard S. Zemel   +8 more
openaire   +2 more sources

Swelling‐Programmed Topographical Guidance for Dynamic Spheroid Self‐Assembly via a Mechanochemical Hydrogel Niche

Advanced Functional Materials, EarlyView.
A swelling‐programmed micropatterned hydrogel guides adherent cells through a controlled transition from cell–matrix anchoring to cadherin‐mediated cell–cell compaction, enabling rapid assembly of high‐viability spheroids with defined size and morphology.
Han Gyeol Nam, Seon Yeong Chae, Young Woo Kwon, Hye Jin Heo, Hye Rin Lee, Ji Hyeok Lee, Dong‐Wook Han, Yun Hak Kim, Suck Won Hong   +8 more
wiley   +1 more source

Intrinsic Photoactive Star ZnPc–Poly(glutamate) Nanoplatforms for Multimodal Glioblastoma Therapy and Brain‐Targeted Delivery

Advanced Functional Materials, EarlyView.
An intrinsic photoactive star‐shaped zinc phtalocyanine‐poly(L‐glutamic acid) (ZnPc‐PGA) nanoplatform for multimodal glioblastoma (GBM) therapy and brain‐targeted elivery. A ZnPc‐PGA‐based multifunctional theranostic nanocarrier platform enables image‐guided, multimodal GBM therapy. ZnPc‐PGA nanocarriers support the integration of fluorescence imaging,
Amina Benaicha‐Fernández, Teodora Ranđelović, Ana Armiñán, Víctor Sebastián, Manuel Fuentes, Cristián Huck‐Iriart, Esther Masiá, Paula Carrascosa‐Marco, Pablo Juanes‐Velasco, Snežana Đorđević, Clara Bayona, Ignacio Ochoa, Maria Medel, Inmaculada Conejos‐Sánchez, María J. Vicent   +14 more
wiley   +1 more source