Results 71 to 80 of about 82,326 (277)

LEAD: Literature Enhanced Ab Initio Discovery of Nitride Dusting Layers for Enhanced Tunnel Magnetoresistance and Lower Resistance Magnetic Tunnel Junctions

Advanced Materials, EarlyView.
Magnetic tunnel junctions (MTJs) using MgO tunnel barriers face challenges of high resistance‐area product and low tunnel magnetoresistance (TMR). To discover alternative materials, Literature Enhanced Ab initio Discovery (LEAD) is developed. The LEAD‐predicted materials are theoretically evaluated, showing that MTJs with dusting of ScN or TiN on ...
Sabiq Islam, William S. Rogers, Chen‐Yu Hu, Ming‐Yuan Song, Xinyu Bao, Shehrin Sayed, Jean Anne C. Incorvia   +6 more
wiley   +1 more source

TO-UGDA: target-oriented unsupervised graph domain adaptation

Scientific Reports
Graph domain adaptation (GDA) aims to address the challenge of limited label data in the target graph domain. Existing methods such as UDAGCN, GRADE, DEAL, and COCO for different-level (node-level, graph-level) adaptation tasks exhibit variations in ...
Zhuo Zeng, Jianyu Xie, Zhijie Yang, Tengfei Ma, Duanbing Chen   +4 more
doaj   +1 more source

Importance Weighted Adversarial Nets for Partial Domain Adaptation

, 2018
This paper proposes an importance weighted adversarial nets-based method for unsupervised domain adaptation, specific for partial domain adaptation where the target domain has less number of classes compared to the source domain.
Ding, Zewei, Li, Wanqing, Ogunbona, Philip, Zhang, Jing   +3 more
core   +1 more source

Hydrogel‐Based Functional Materials: Classifications, Properties, and Applications

Advanced Materials Technologies, EarlyView.
Conductive hydrogels have emerged as promising materials for smart wearable devices due to their outstanding flexibility, multifunctionality, and biocompatibility. This review systematically summarizes recent progress in their design strategies, focusing on monomer systems and conductive components, and highlights key multifunctional properties such as
Zeyu Zhang, Zao Cheng, Patrizio Raffa
wiley   +1 more source

Unsupervised Domain Adaptation via Contrastive Learning and Complementary Region-Class Mixing

IEEE Access
In semantic segmentation, current deep convolutional neural networks rely heavily on extensive data to achieve superior segmentation results. However, these deep models have poor generalization ability across different domain datasets.
Xiaojing Li, Wei Zhou, Mingjian Jiang
doaj   +1 more source

Unsupervised Domain Adaptation using Graph Transduction Games

, 2019
Unsupervised domain adaptation (UDA) amounts to assigning class labels to the unlabeled instances of a dataset from a target domain, using labeled instances of a dataset from a related source domain.
Aslan, Sinem, Marchiori, Elena, Pelillo, Marcello, Torcinovich, Alessandro, van Laarhoven, Twan, Vascon, Sebastiano   +5 more
core   +1 more source

Flexible Sensor‐Based Human–Machine Interfaces with AI Integration for Medical Robotics

Advanced Robotics Research, EarlyView.
This review explores how flexible sensing technology and artificial intelligence (AI) significantly enhance human–machine interfaces in medical robotics. It highlights key sensing mechanisms, AI‐driven advancements, and applications in prosthetics, exoskeletons, and surgical robotics.
Yuxiao Wang, Zhipeng Jiang, Sun Hwa Kwon, Matthew Ibrahim, Alexander Dang, Lin Dong   +5 more
wiley   +1 more source

Maximum Classifier Discrepancy for Unsupervised Domain Adaptation

, 2018
In this work, we present a method for unsupervised domain adaptation. Many adversarial learning methods train domain classifier networks to distinguish the features as either a source or target and train a feature generator network to mimic the ...
Harada, Tatsuya, Saito, Kuniaki, Ushiku, Yoshitaka, Watanabe, Kohei   +3 more
core   +1 more source

The Future of Research in Cognitive Robotics: Foundation Models or Developmental Cognitive Models?

Advanced Robotics Research, EarlyView.
Research in cognitive robotics founded on principles of developmental psychology and enactive cognitive science would yield what we seek in autonomous robots: the ability to perceive its environment, learn from experience, anticipate the outcome of events, act to pursue goals, and adapt to changing circumstances without resorting to training with ...
David Vernon
wiley   +1 more source

Triplet Loss Network for Unsupervised Domain Adaptation

Algorithms, 2019
Domain adaptation is a sub-field of transfer learning that aims at bridging the dissimilarity gap between different domains by transferring and re-using the knowledge obtained in the source domain to the target domain.
Imad Eddine Ibrahim Bekkouch, Youssef Youssry, Rustam Gafarov, Adil Khan, Asad Masood Khattak   +4 more
doaj   +1 more source