Zobrazeno 1 - 10
of 22
pro vyhledávání: '"Dakun Yang"'
Autor:
Dakun Yang, Wei Wu
Publikováno v:
Discrete Dynamics in Nature and Society, Vol 2012 (2012)
In many applications, it is natural to use interval data to describe various kinds of uncertainties. This paper is concerned with an interval neural network with a hidden layer. For the original interval neural network, it might cause oscillation in
Externí odkaz:
https://doaj.org/article/b96ba308fece460c9dad8468809c0156
Autor:
Dakun Yang, Liping He
Publikováno v:
2022 4th International Conference on Electrical Engineering and Control Technologies (CEECT).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::40bc0a375ad62bd1cfe5aa67902b608f
https://doi.org/10.1109/ceect55960.2022.10030226
https://doi.org/10.1109/ceect55960.2022.10030226
Publikováno v:
Neural Processing Letters. 50:1589-1609
In order to broaden the study of the most popular and general Takagi–Sugeno (TS) system, we propose a complex-valued neuro-fuzzy inference system which realises the zero-order TS system in the complex-valued network architecture and develop it. In
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::af129d8e555c8b87dc95252d585dcbe0
https://doi.org/10.1007/s11063-018-9949-7
https://doi.org/10.1007/s11063-018-9949-7
Publikováno v:
Journal of the Franklin Institute. 355:6132-6151
This paper investigates an evolving split-complex valued neuro-fuzzy (SCVNF) algorithm for Takagi–Sugeno–Kang (TSK) system. In a bid to avoid the contradiction between boundedness and analyticity, splitting technique is traditionally employed to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b6357e47cb6885485c6d04d3cd3fd6e0
https://doi.org/10.1016/j.jfranklin.2018.06.015
https://doi.org/10.1016/j.jfranklin.2018.06.015
Autor:
Dakun Yang, Yan Liu
Publikováno v:
Neurocomputing. 272:122-129
Interval neural networks can easily address uncertain information, since they are capable of handling various kinds of uncertainties inherently which are represented by interval. L q (0 q L 1 regularization for better solution of sparsity problems, a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4d3f6b3deab00968e0bf1563b7a3a8d6
https://doi.org/10.1016/j.neucom.2017.06.061
https://doi.org/10.1016/j.neucom.2017.06.061
Publikováno v:
Neurocomputing. 272:163-169
The properties of a boundedness estimations are investigated during the training of online back-propagation method with L 2 regularizer for Sigma-Pi-Sigma neural network. This brief presents a unified convergence analysis, exploiting theorems of Whit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bb982d2f61ef2719ce90dfa1ca7f432f
https://doi.org/10.1016/j.neucom.2017.06.057
https://doi.org/10.1016/j.neucom.2017.06.057
Autor:
Yan Liu, Dakun Yang
Publikováno v:
Fuzzy Sets and Systems. 319:28-49
It has been proven that Takagi–Sugeno systems are universal approximators, and they are applied widely to classification and regression problems. The main challenges of these models are convergence analysis and their computational complexity due to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f19b05df0cf6e7600943993f79999268
https://doi.org/10.1016/j.fss.2016.07.003
https://doi.org/10.1016/j.fss.2016.07.003
Publikováno v:
Pattern Recognition and Computer Vision ISBN: 9783030033347
PRCV (2)
PRCV (2)
Human body detection is a key technology in the fields of biometric recognition, and the detection in a depth image is rather challenging due to serious noise effects and lack of texture information. For addressing this issue, we propose the feature
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::54a0ed15d360ed52b02d4d70d8d1025c
https://doi.org/10.1007/978-3-030-03335-4_8
https://doi.org/10.1007/978-3-030-03335-4_8
Publikováno v:
Neural Processing Letters. 43:745-758
By combining of the benefits of high-order network and TSK (Tagaki-Sugeno-Kang) inference system, Pi-Sigma network is capable to dispose with the nonlinear problems much more effectively, which means it has a compacter construction, and quicker compu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::49d923babe968e8e3df1514f209ea4aa
https://doi.org/10.1007/s11063-015-9445-2
https://doi.org/10.1007/s11063-015-9445-2
Publikováno v:
Neurocomputing. 151:333-341
Sigma–Pi–Sigma neural networks are known to provide more powerful mapping capability than traditional feed-forward neural networks. The L1/2 regularizer is very useful and efficient, and can be taken as a representative of all the L q ( 0 q 1 ) r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::60536d4849ca22ad828557af5ddb592b
https://doi.org/10.1016/j.neucom.2014.09.031
https://doi.org/10.1016/j.neucom.2014.09.031