Zobrazeno 1 - 10
of 590
pro vyhledávání: '"Wang, Dianhui"'
Autor:
Yan, Xiufeng, Wang, Dianhui
Stochastic Configuration Networks (SCNs) are a class of randomized neural networks that integrate randomized algorithms within an incremental learning framework. A defining feature of SCNs is the supervisory mechanism, which adaptively adjusts the di
Externí odkaz:
http://arxiv.org/abs/2411.08544
Autor:
Dang, Gang, Wang, Dianhui
Deep learning techniques have shown promise in many domain applications. This paper proposes a novel deep reservoir computing framework, termed deep recurrent stochastic configuration network (DeepRSCN) for modelling nonlinear dynamic systems. DeepRS
Externí odkaz:
http://arxiv.org/abs/2410.20904
Autor:
Dang, Gang, Wang, Dianhui
Recurrent stochastic configuration networks (RSCNs) are a class of randomized learner models that have shown promise in modelling nonlinear dynamics. In many fields, however, the data generated by industry systems often exhibits nonstationary charact
Externí odkaz:
http://arxiv.org/abs/2410.10072
Autor:
Wang, Dianhui, Dang, Gang
This paper presents a novel neuro-fuzzy model, termed fuzzy recurrent stochastic configuration networks (F-RSCNs), for industrial data analytics. Unlike the original recurrent stochastic configuration network (RSCN), the proposed F-RSCN is constructe
Externí odkaz:
http://arxiv.org/abs/2407.11038
Autor:
Wang, Dianhui, Dang, Gang
Temporal data modelling techniques with neural networks are useful in many domain applications, including time-series forecasting and control engineering. This paper aims at developing a recurrent version of stochastic configuration networks (RSCNs)
Externí odkaz:
http://arxiv.org/abs/2406.16959
Autor:
Felicetti, Matthew J., Wang, Dianhui
Neural networks for industrial applications generally have additional constraints such as response speed, memory size and power usage. Randomized learners can address some of these issues. However, hardware solutions can provide better resource reduc
Externí odkaz:
http://arxiv.org/abs/2310.19225
Autor:
Wang, Dianhui, Felicetti, Matthew J.
Real-time predictive modelling with desired accuracy is highly expected in industrial artificial intelligence (IAI), where neural networks play a key role. Neural networks in IAI require powerful, high-performance computing devices to operate a large
Externí odkaz:
http://arxiv.org/abs/2308.13570
Autor:
Chen, Qiaobing, He, Zijian, Zhao, Yi, Liu, Xuan, Wang, Dianhui, Zhong, Yan, Hu, Chaohao, Hao, Chenggang, Lu, Kecheng, Wang, Zhongmin
Publikováno v:
In Materials & Design October 2024 246
