Propagation and control of stochastic signals through universal learning networks

Kotaro Hirasawa, Shingo Mabu, Takayuki Furuzuki

研究成果: Article

19 引用 (Scopus)

抄録

The way of propagating and control of stochastic signals through Universal Learning Networks (ULNs) and its applications are proposed. ULNs have been already developed to form a superset of neural networks and have been applied as a universal framework for modeling and control of non-linear large-scale complex systems. However, the ULNs cannot deal with stochastic variables. Deterministic signals can be propagated through a ULN, but the ULN does not provide any stochastic characteristics of the signals propagating through it. The proposed method named Probabilistic Universal Learning Networks (PrULNs) can process stochastic variables and can train network parameters so that the signals behave with the pre-specified stochastic properties. As examples of applications of the proposed method, control and identification of non-linear dynamic systems with noises are studied, and it is shown that the method are useful for dealing with the control and identification of the non-linear stochastic systems contaminated with noises.

元の言語English
ページ(範囲)487-499
ページ数13
ジャーナルNeural Networks
19
発行部数4
DOI
出版物ステータスPublished - 2006 5

Fingerprint

Learning
Noise
Stochastic systems
Random processes
Stochastic Processes
Large scale systems
Dynamical systems
Nonlinear Dynamics
Neural networks

ASJC Scopus subject areas

  • Artificial Intelligence
  • Neuroscience(all)

これを引用

Propagation and control of stochastic signals through universal learning networks. / Hirasawa, Kotaro; Mabu, Shingo; Furuzuki, Takayuki.

:: Neural Networks, 巻 19, 番号 4, 05.2006, p. 487-499.

研究成果: Article

Hirasawa, Kotaro ; Mabu, Shingo ; Furuzuki, Takayuki. / Propagation and control of stochastic signals through universal learning networks. :: Neural Networks. 2006 ; 巻 19, 番号 4. pp. 487-499.
@article{c1cc00b4e44542348ebf4dda54bdf06e,
title = "Propagation and control of stochastic signals through universal learning networks",
abstract = "The way of propagating and control of stochastic signals through Universal Learning Networks (ULNs) and its applications are proposed. ULNs have been already developed to form a superset of neural networks and have been applied as a universal framework for modeling and control of non-linear large-scale complex systems. However, the ULNs cannot deal with stochastic variables. Deterministic signals can be propagated through a ULN, but the ULN does not provide any stochastic characteristics of the signals propagating through it. The proposed method named Probabilistic Universal Learning Networks (PrULNs) can process stochastic variables and can train network parameters so that the signals behave with the pre-specified stochastic properties. As examples of applications of the proposed method, control and identification of non-linear dynamic systems with noises are studied, and it is shown that the method are useful for dealing with the control and identification of the non-linear stochastic systems contaminated with noises.",
keywords = "Forward propagation, Gradient method, Neural networks, Non-linear systems, Probabilistic networks, Stochastic signals",
author = "Kotaro Hirasawa and Shingo Mabu and Takayuki Furuzuki",
year = "2006",
month = "5",
doi = "10.1016/j.neunet.2005.10.005",
language = "English",
volume = "19",
pages = "487--499",
journal = "Neural Networks",
issn = "0893-6080",
publisher = "Elsevier Limited",
number = "4",

}

TY - JOUR

T1 - Propagation and control of stochastic signals through universal learning networks

AU - Hirasawa, Kotaro

AU - Mabu, Shingo

AU - Furuzuki, Takayuki

PY - 2006/5

Y1 - 2006/5

N2 - The way of propagating and control of stochastic signals through Universal Learning Networks (ULNs) and its applications are proposed. ULNs have been already developed to form a superset of neural networks and have been applied as a universal framework for modeling and control of non-linear large-scale complex systems. However, the ULNs cannot deal with stochastic variables. Deterministic signals can be propagated through a ULN, but the ULN does not provide any stochastic characteristics of the signals propagating through it. The proposed method named Probabilistic Universal Learning Networks (PrULNs) can process stochastic variables and can train network parameters so that the signals behave with the pre-specified stochastic properties. As examples of applications of the proposed method, control and identification of non-linear dynamic systems with noises are studied, and it is shown that the method are useful for dealing with the control and identification of the non-linear stochastic systems contaminated with noises.

AB - The way of propagating and control of stochastic signals through Universal Learning Networks (ULNs) and its applications are proposed. ULNs have been already developed to form a superset of neural networks and have been applied as a universal framework for modeling and control of non-linear large-scale complex systems. However, the ULNs cannot deal with stochastic variables. Deterministic signals can be propagated through a ULN, but the ULN does not provide any stochastic characteristics of the signals propagating through it. The proposed method named Probabilistic Universal Learning Networks (PrULNs) can process stochastic variables and can train network parameters so that the signals behave with the pre-specified stochastic properties. As examples of applications of the proposed method, control and identification of non-linear dynamic systems with noises are studied, and it is shown that the method are useful for dealing with the control and identification of the non-linear stochastic systems contaminated with noises.

KW - Forward propagation

KW - Gradient method

KW - Neural networks

KW - Non-linear systems

KW - Probabilistic networks

KW - Stochastic signals

UR - http://www.scopus.com/inward/record.url?scp=33746877500&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33746877500&partnerID=8YFLogxK

U2 - 10.1016/j.neunet.2005.10.005

DO - 10.1016/j.neunet.2005.10.005

M3 - Article

C2 - 16423502

AN - SCOPUS:33746877500

VL - 19

SP - 487

EP - 499

JO - Neural Networks

JF - Neural Networks

SN - 0893-6080

IS - 4

ER -