Zobrazeno 1 - 10
of 28
pro vyhledávání: '"Dokkyun Yi"'
Publikováno v:
Applied Sciences, Vol 11, Iss 2, p 850 (2021)
Artificial intelligence (AI) is achieved by optimizing the cost function constructed from learning data. Changing the parameters in the cost function is an AI learning process (or AI learning for convenience). If AI learning is well performed, then t
Externí odkaz:
https://doaj.org/article/8c096e11d9374544ad74abcecbd5f655
Publikováno v:
Symmetry, Vol 12, Iss 4, p 615 (2020)
This paper analyzes the operation principle and predicted value of the recurrent-neural-network (RNN) structure, which is the most basic and suitable for the change of time in the structure of a neural network for various types of artificial intellig
Externí odkaz:
https://doaj.org/article/58b7502f40f741c180563ef5fe5b77de
Publikováno v:
Symmetry, Vol 12, Iss 4, p 660 (2020)
The process of machine learning is to find parameters that minimize the cost function constructed by learning the data. This is called optimization and the parameters at that time are called the optimal parameters in neural networks. In the process o
Externí odkaz:
https://doaj.org/article/1a54bcf3652d40ef810a3243e878465e
Publikováno v:
Applied Sciences, Vol 10, Iss 3, p 1073 (2020)
A machine is taught by finding the minimum value of the cost function which is induced by learning data. Unfortunately, as the amount of learning increases, the non-liner activation function in the artificial neural network (ANN), the complexity of t
Externí odkaz:
https://doaj.org/article/b972701a1284486cbb0b2d0869a3d22b
Publikováno v:
Symmetry, Vol 11, Iss 7, p 912 (2019)
The concept of trend in data and a novel neural network method for the forecasting of upcoming time-series data are proposed in this paper. The proposed method extracts two data sets—the trend and the remainder—resulting in two separate learning
Externí odkaz:
https://doaj.org/article/19c7666791ca444e9b3c516fb02deb89
Publikováno v:
Symmetry, Vol 11, Iss 7, p 942 (2019)
A The learning process of machine learning consists of finding values of unknown weights in a cost function by minimizing the cost function based on learning data. However, since the cost function is not convex, it is conundrum to find the minimum va
Externí odkaz:
https://doaj.org/article/e6b0d8c22a774a6e87b5401640fe6890
Publikováno v:
2022 IEEE/ACIS 7th International Conference on Big Data, Cloud Computing, and Data Science (BCD).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d36081d0e9692aaedd4352ebfce489ed
https://doi.org/10.1109/bcd54882.2022.9900580
https://doi.org/10.1109/bcd54882.2022.9900580
Publikováno v:
Applied Sciences
Volume 10
Issue 3
Applied Sciences, Vol 10, Iss 3, p 1073 (2020)
Volume 10
Issue 3
Applied Sciences, Vol 10, Iss 3, p 1073 (2020)
A machine is taught by finding the minimum value of the cost function which is induced by learning data. Unfortunately, as the amount of learning increases, the non-liner activation function in the artificial neural network (ANN), the complexity of t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::21bc5cffac87965834a286181ebe7a49
Autor:
Sunyoung Bu, Dokkyun Yi
Publikováno v:
Journal of Computational and Applied Mathematics. 324:1-16
In this paper, we introduce a mass conservative scheme for solving the Vlasov–Poisson equation. This scheme is based on an Eulerian approach and is constructed using an interpolation scheme with limiters. In order to preserve the mass, the differen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5abd41320bd3043c99b0ddfcff21b33a
https://doi.org/10.1016/j.cam.2017.04.019
https://doi.org/10.1016/j.cam.2017.04.019
Publikováno v:
Symmetry, Vol 11, Iss 7, p 912 (2019)
Symmetry
Volume 11
Issue 7
Symmetry
Volume 11
Issue 7
The concept of trend in data and a novel neural network method for the forecasting ofupcoming time-series data are proposed in this paper. The proposed method extracts two datasets&mdash
the trend and the remainder&mdash
resulting in two se
the trend and the remainder&mdash
resulting in two se
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::065615f50b8ccbd2a8b3ab70b4a58408
https://www.mdpi.com/2073-8994/11/7/912
https://www.mdpi.com/2073-8994/11/7/912