UM

Browse/Search Results:  1-3 of 3 Help

Selected(0)Clear Items/Page:    Sort:
Heterogeneity-Aware Memory Efficient Federated Learning via Progressive Layer Freezing Conference paper
Wu, Yebo, Li, Li, Tian, Chunlin, Chang, Tao, Lin, Chi, Wang, Cong, Xu, Cheng Zhong. Heterogeneity-Aware Memory Efficient Federated Learning via Progressive Layer Freezing[C]:Institute of Electrical and Electronics Engineers Inc., 2024.
Authors:  Wu, Yebo;  Li, Li;  Tian, Chunlin;  Chang, Tao;  Lin, Chi; et al.
Favorite | TC[WOS]:0 TC[Scopus]:0 | Submit date:2024/11/05
Federated Learning  Heterogeneous Memory  On-device Training  Training  Accuracy  Runtime  Perturbation Methods  Memory Management  Quality Of Service  
Power Synchronization Control of Grid-Tied Inverter: Phase Error Modeling for Unified System Design Journal article
Liu, Ao, Hou, Chuanchuan, Zhu, Miao, Dai, Ningyi. Power Synchronization Control of Grid-Tied Inverter: Phase Error Modeling for Unified System Design[J]. IEEE Journal of Emerging and Selected Topics in Power Electronics, 2024, 12(4), 3650-3662.
Authors:  Liu, Ao;  Hou, Chuanchuan;  Zhu, Miao;  Dai, Ningyi
Favorite | TC[WOS]:0 TC[Scopus]:0  IF:4.6/5.3 | Submit date:2024/06/05
Small-signal Model  Inverters  Synchronization  Perturbation Methods  System Analysis And Design  
Addi-Reg: A Better Generalization-Optimization Tradeoff Regularization Method for Convolutional Neural Networks Journal article
Yao Lu, Zheng Zhang, Guangming Lu, Yicong Zhou, Jinxing Li, David Zhang. Addi-Reg: A Better Generalization-Optimization Tradeoff Regularization Method for Convolutional Neural Networks[J]. IEEE Transactions on Cybernetics, 2021, 52(10), 10827-10842.
Authors:  Yao Lu;  Zheng Zhang;  Guangming Lu;  Yicong Zhou;  Jinxing Li; et al.
Favorite | TC[WOS]:11 TC[Scopus]:8  IF:9.4/10.3 | Submit date:2022/05/13
Additional Regularization (Addi-reg)  Convergence  Convolutional Neural Networks (Cnns)  Deep Learning  Learning Systems  Multiplicative Regularization (Multi-reg)  Neural Networks  Optimization  Perturbation Methods  Regularization.  Residual Neural Networks  Training