Results 71 to 80 of about 6,308,360 (314)

Federated Balanced Learning

CoRR
Federated learning is a paradigm of joint learning in which clients collaborate by sharing model parameters instead of data. However, in the non-iid setting, the global model experiences client drift, which can seriously affect the final performance of the model.
Jiaze Li, Haoran Xu, Wanyi Wu, Changwei Wang 0001, Shuaiguang Li, Jianzhong Ju, Zhenbo Luo, Jian Luan 0001, Youyang Qu, Longxiang Gao, Xudong Yang, Lumin Xing   +11 more
openaire   +3 more sources

Intelligent Maintenance Review for Robots: Multimodal Information, Deep Diagnosis and Embodied Artificial Intelligence

Advanced Robotics Research, EarlyView.
This review maps the methods to monitor robots’ health by fusing vibration, sound, control signals, vision, force, and oil information with artificial intelligence. It identifies deep learning, transfer learning, digital twins, and physics‐informed models as key methodological pathways enabling earlier diagnosis, safer human–robot collaboration, and ...
Yuting Qiao, Hongbo Wang, Naipeng Li, Shuo Wang, Yaguo Lei, Tonghai Wu, Junyi Cao   +6 more
wiley   +1 more source

Class Incremental Learning in a Federated setting

, 2022
reservedIl federated learning (FL) è un paradigma di apprendimento introdotto recentemente che consente di addestrare modelli utilizzando training data che possono essere distribuiti tra più dispositivi e/o data center.
RIGON, ALBERTO
core  

Ethical Precision in Nanoscale Brain Interfacing

Advanced Science, EarlyView.
As brain interfaces approach the nanoscale, precision no longer only measures—it knows, predicts, and potentially reshapes the mind. This work argues that traditional ethics fails under such conditions and proposes a shift toward continuous, operation‐based governance using the recovery–discovery framework to track, constrain, and responsibly steer ...
Guilherme Wood
wiley   +1 more source

Distributed consensus problem with caching on federated learning framework

International Journal of Distributed Sensor Networks, 2022
Federated learning framework facilitates more applications of deep learning algorithms on the existing network architectures, where the model parameters are aggregated in a centralized manner.
Xin Yan, Yiming Qin, Xiaodong Hu, Xiaoling Xiao   +3 more
doaj   +1 more source

Tumor Exposomics: A New Paradigm for Individualized Continuous Exposure Monitoring

Advanced Science, EarlyView.
Tumor exposomics integrates continuous monitoring of environmental exposures, endogenous biological responses, and behavioral factors within a unified temporal framework. By combining multimodal sensing technologies with AI‐enabled causal modeling, this emerging paradigm reconstructs exposure‐damage trajectories and supports individualized dynamic risk
Kaicheng Shen, Weiyi Wang, Yang Wang, Yiqiang Wu, Xiaohong Liu, Wei Zhang, Juanjuan Ou   +6 more
wiley   +1 more source

Network Anomaly Detection Using Federated Learning and Transfer Learning

, 2020
Since deep neural networks can learn data representation from training data automatically, deep learning methods are widely used in the network anomaly detection.
Jian Teng, Guo, Qianling, Ying Zhao, Qianling Guo, Di Wu, Chen, Junjun, Teng, Jian, Wu, Di, Junjun Chen, Zhao, Ying   +9 more
core   +1 more source

Closing the Loop: High‐Precision 3D Photofabrication in Living Tissues

Advanced Science, EarlyView.
Writing 3D microstructures inside living tissue demands more than laser access; It demands information. Hierarchical sensing captures thermal and mechanical states across pulse‐train, voxel, and structure timescales, feeding a controller that steers the laser in real time.
Amirbahador Zeynali, Mangirdas Malinauskas, Giuseppe Chirico   +2 more
wiley   +1 more source

A survey of security threats in federated learning

Complex & Intelligent Systems
Federated learning is a distributed machine learning paradigm that emerged as a solution to the need for privacy protection in artificial intelligence.
Yunhao Feng, Yanming Guo, Yinjian Hou, Yulun Wu, Mingrui Lao, Tianyuan Yu, Gang Liu   +6 more
doaj   +1 more source

A Survey of Differential Privacy Techniques for Federated Learning

IEEE Access
The problem of data privacy protection in the information age deserves people’s attention. As a distributed machine learning technology, federated learning can effectively solve the problem of privacy security and data silos.
Wang Xin, Li Jiaqian, Ding Xueshuang, Zhang Haoji, Sun Lianshan   +4 more
doaj   +1 more source