Zobrazeno 1 - 10
of 310
pro vyhledávání: '"Chi-Sing Leung"'
Publikováno v:
IEEE Access, Vol 9, Pp 112955-112965 (2021)
The Boltzmann machine (BM) and restricted Boltzmann machine (RBM) models are representative stochastic neural networks, in which neuron states are determined by stochastic activation functions. They are widely used in many applications. However, when
Externí odkaz:
https://doaj.org/article/a8e718dcf175404a87301c5ff59ba29e
Publikováno v:
Mathematics, Vol 10, Iss 24, p 4730 (2022)
The single-layer perceptron, introduced by Rosenblatt in 1958, is one of the earliest and simplest neural network models. However, it is incapable of classifying linearly inseparable patterns. A new era of neural network research started in 1986, whe
Externí odkaz:
https://doaj.org/article/e784970775534add8087c4f9dbe6c69f
Publikováno v:
Mathematics, Vol 10, Iss 24, p 4801 (2022)
Many analog neural network approaches for sparse recovery were based on using ℓ1-norm as the surrogate of ℓ0-norm. This paper proposes an analog neural network model, namely the Lagrange programming neural network with ℓp objective and quadrati
Externí odkaz:
https://doaj.org/article/e3134b304bd9439982547ef26f4425b4
Publikováno v:
IEEE Access, Vol 7, Pp 151902-151914 (2019)
There are two important issues in the construction of a radial basis function (RBF) neural network. The first one is to select suitable RBF centers. The second one is that the resultant RBF network should be with good fault tolerance. This paper prop
Externí odkaz:
https://doaj.org/article/76535e78199e4093bc34c979bdbf61f7
Publikováno v:
IEEE Access, Vol 9, Pp 81296-81313 (2021)
Vectorized visibility is a powerful visibility representation for rendering direct illumination with all frequency quality. However, the existing rendering method requires the visibility functions to be synthesized three times, followed with three ra
Externí odkaz:
https://doaj.org/article/f944b713629942408a1af3bf117a2487
Publikováno v:
Neurocomputing. 532:77-93
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::20ccdfd4b62c4ff479e16fa6252474a1
https://doi.org/10.1016/j.neucom.2023.02.012
https://doi.org/10.1016/j.neucom.2023.02.012
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cd2cfb6d4426881f6a1a8980472a93f1
https://doi.org/10.1109/icassp49357.2023.10094771
https://doi.org/10.1109/icassp49357.2023.10094771
Publikováno v:
IEEE Transactions on Antennas and Propagation. 70:5209-5216
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ad0779b03d25e0db6d32292dea793426
https://doi.org/10.1109/tap.2022.3146860
https://doi.org/10.1109/tap.2022.3146860
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 33:3184-3192
The dual neural network-based k-winner-take-all (DNN-kWTA) is an analog neural model that is used to identify the k largest numbers from n inputs. Since threshold logic units (TLUs) are key elements in the model, offset voltage drifts in TLUs may aff
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::38da6d62dd3c3315aa9a8918e476c7a5
https://doi.org/10.1109/tnnls.2021.3050493
https://doi.org/10.1109/tnnls.2021.3050493
Publikováno v:
Neurocomputing. 486:200-214
This paper investigates noise/fault tolerant incremental algorithms for the extreme learning machine (ELM) concept. Existing incremental ELM algorithms can be classified into two approaches: non-recomputation and recomputation. This paper first formu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::412a73c3590325e0269f0f312e1adf25
https://doi.org/10.1016/j.neucom.2021.11.026
https://doi.org/10.1016/j.neucom.2021.11.026