Zobrazeno 1 - 10
of 892
pro vyhledávání: '"Tong, Kai"'
In the field of autonomous driving, even a meticulously trained model can encounter failures when faced with unfamiliar sceanrios. One of these scenarios can be formulated as an online continual learning (OCL) problem. That is, data come in an online
Externí odkaz:
http://arxiv.org/abs/2405.17779
Autor:
Zhuang, Huiping, He, Run, Tong, Kai, Fang, Di, Sun, Han, Li, Haoran, Chen, Tianyi, Zeng, Ziqian
In this paper, we introduce analytic federated learning (AFL), a new training paradigm that brings analytical (i.e., closed-form) solutions to the federated learning (FL) community. Our AFL draws inspiration from analytic learning -- a gradient-free
Externí odkaz:
http://arxiv.org/abs/2405.16240
Class-incremental learning (CIL) under an exemplar-free constraint has presented a significant challenge. Existing methods adhering to this constraint are prone to catastrophic forgetting, far more so than replay-based techniques that retain access t
Externí odkaz:
http://arxiv.org/abs/2403.17503
Autor:
Zhuang, Huiping, Liu, Yuchen, He, Run, Tong, Kai, Zeng, Ziqian, Chen, Cen, Wang, Yi, Chau, Lap-Pui
Online Class Incremental Learning (OCIL) aims to train the model in a task-by-task manner, where data arrive in mini-batches at a time while previous data are not accessible. A significant challenge is known as Catastrophic Forgetting, i.e., loss of
Externí odkaz:
http://arxiv.org/abs/2403.15751
Autor:
Zhuang, Huiping, Chen, Yizhu, Fang, Di, He, Run, Tong, Kai, Wei, Hongxin, Zeng, Ziqian, Chen, Cen
Class incremental learning (CIL) trains a network on sequential tasks with separated categories but suffers from catastrophic forgetting, where models quickly lose previously learned knowledge when acquiring new tasks. The generalized CIL (GCIL) aims
Externí odkaz:
http://arxiv.org/abs/2403.15706
Exemplar-free class-incremental learning (EFCIL) aims to mitigate catastrophic forgetting in class-incremental learning without available historical data. Compared with its counterpart (replay-based CIL) that stores historical samples, the EFCIL suff
Externí odkaz:
http://arxiv.org/abs/2403.13522
Publikováno v:
Research 6, 0134 (2023)
Neural networks have achieved impressive breakthroughs in both industry and academia. How to effectively develop neural networks on quantum computing devices is a challenging open problem. Here, we propose a new quantum neural network model for quant
Externí odkaz:
http://arxiv.org/abs/2305.08544
Publikováno v:
In Measurement August 2024 235
Autor:
Tong, Kai-wen, Yu, Fei, Dai, Zhang-jun, Wang, Hao, Huang, Kang, Chen, Shan-xiong, Guo, Jian-hua
Publikováno v:
In Powder Technology 1 July 2024 443
Publikováno v:
In Applied Soft Computing July 2024 159