Results 61 to 70 of about 30,335 (256)

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

Unleashing the Power of Machine Learning in Nanomedicine Formulation Development

Advanced Functional Materials, EarlyView.
A random forest machine learning model is able to make predictions on nanoparticle attributes of different nanomedicines (i.e. lipid nanoparticles, liposomes, or PLGA nanoparticles) based on microfluidic formulation parameters. Machine learning models are based on a database of nanoparticle formulations, and models are able to generate unique solutions
Thomas L. Moore, Cristiano Pesce, Antonietta Greco, Claudia Pisante, Greta Avancini, Valentina Di Francesco, Yosi Shamay, Paolo Decuzzi   +7 more
wiley   +1 more source

A multi-view contrastive learning for heterogeneous network embedding

Scientific Reports, 2023
Graph contrastive learning has been developed to learn discriminative node representations on homogeneous graphs. However, it is not clear how to augment the heterogeneous graphs without substantially altering the underlying semantics or how to design ...
Qi Li, Wenping Chen, Zhaoxi Fang, Changtian Ying, Chen Wang   +4 more
doaj   +1 more source

Smarter Sensors Through Machine Learning: Historical Insights and Emerging Trends across Sensor Technologies

Advanced Functional Materials, EarlyView.
This review highlights how machine learning (ML) algorithms are employed to enhance sensor performance, focusing on gas and physical sensors such as haptic and strain devices. By addressing current bottlenecks and enabling simultaneous improvement of multiple metrics, these approaches pave the way toward next‐generation, real‐world sensor applications.
Kichul Lee, Osman Gul, Yeongjae Kwon, Jaeseok Jeong, Seokjoo Cho, Jihyeon Ahn, Jehee Yu, Cheolmin Kim, Donho Lee, Hyeonseok Han, Byeongju Lee, Jungrak Choi, Ji‐Hwan Ha, Yongrok Jeong, Kyungnam Kang, Ali Javey, Junseong Ahn, Inkyu Park   +17 more
wiley   +1 more source

Learning from Feature and Global Topologies: Adaptive Multi-View Parallel Graph Contrastive Learning

Mathematics
To address the limitations of existing graph contrastive learning methods, which fail to adaptively integrate feature and topological information and struggle to efficiently capture multi-hop information, we propose an adaptive multi-view parallel graph ...
Yumeng Song, Xiaohua Li, Fangfang Li, Ge Yu   +3 more
doaj   +1 more source

Localized Contrastive Learning on Graphs

, 2022
Contrastive learning methods based on InfoNCE loss are popular in node representation learning tasks on graph-structured data. However, its reliance on data augmentation and its quadratic computational complexity might lead to inconsistency and inefficiency problems.
Zhang, Hengrui, Wu, Qitian, Wang, Yu, Zhang, Shaofeng, Yan, Junchi, Yu, Philip S.   +5 more
openaire   +2 more sources

Toward Scalable Solutions for Silver‐Based Gas Diffusion Electrode Fabrication for the Electrochemical Conversion of CO2 – A Perspective

Advanced Functional Materials, EarlyView.
In this study, the preparation techniques for silver‐based gas diffusion electrodes used for the electrochemical reduction of carbon dioxide (eCO2R) are systematically reviewed and compared with respect to their scalability. In addition, physics‐based and data‐driven modeling approaches are discussed, and a perspective is given on how modeling can aid ...
Simon Emken, K. Ashoke Raman, Alexander Bauer, Violeta Karyofylli, Eva Jodat, André Karl, Rüdiger‐A. Eichel   +6 more
wiley   +1 more source

Multi-View Graph Contrastive Neural Networks for Session-Based Recommendation

Mathematics
Session-based recommendation (SBR) aims to predict the next item a user may interact with based on an anonymous session, playing a crucial role in real-time recommendation scenarios.
Pengbo Huang, Chun Wang
doaj   +1 more source

Bio‐Orthogonally Crosslinked Supramolecular Polymer Bottlebrush Hydrogels for Long‐Term 3D Cell Culture

Advanced Functional Materials, EarlyView.
Fibrous benzenetrispeptide (BTP) hydrogels, fabricated via strain‐promoted azide‐alkyne cycloaddition (SPAAC) crosslinking, form robust, bioinert networks. These hydrogels can support 3D cell culture, where cell viability and colony growth depend on the fiber content.
Ceren C. Pihlamagi, David Pretzel, Peer Nölte, Kourosh Rezaei, Ulrich S. Schubert, Johannes C. Brendel   +5 more
wiley   +1 more source

Self-Supervised Heterogeneous Graph Neural Network with Multi-scale Meta-Path Contrastive Learning

International Journal of Computational Intelligence Systems
Heterogeneous graph neural networks (HGNNs) have showcased exceptional modeling prowess in characterizing intricate structures and diverse semantic information.
Yufei Wu, Xiumei Wen, Fanxing Meng, Yingxue Mu   +3 more
doaj   +1 more source