System identification using neural network with parametric sigmoid function

M. Hasheminejad; J. Murata; K. Hirasawa

System identification using neural network with parametric sigmoid function

M. Hasheminejad, J. Murata, K. Hirasawa

Section of Measurement and Control Engineering

Research output: Contribution to conference › Paper › peer-review

Abstract

Nonlinear systems can be modeled by neural networks. However choice of suitable network architecture is the most important problem. And 'how to find the best activation function' is a persistent aspect of the architecture design. Here we have proposed a sigmoid function with one parameter which provides us not only the reduction of error bound but also the opportunity of obtaining better insight into the systems.

Original language	English
Pages	39-44
Number of pages	6
Publication status	Published - Dec 1 1994
Event	Proceedings of the Artificial Neural Networks in Engineering Conference (ANNIE'94) - St. Louis, MO, USA Duration: Nov 13 1994 → Nov 16 1994

Conference

Conference	Proceedings of the Artificial Neural Networks in Engineering Conference (ANNIE'94)
City	St. Louis, MO, USA
Period	11/13/94 → 11/16/94

All Science Journal Classification (ASJC) codes

Engineering(all)

Cite this

@conference{fe41f72510df48029d6d4c7b41ef417f,

title = "System identification using neural network with parametric sigmoid function",

abstract = "Nonlinear systems can be modeled by neural networks. However choice of suitable network architecture is the most important problem. And 'how to find the best activation function' is a persistent aspect of the architecture design. Here we have proposed a sigmoid function with one parameter which provides us not only the reduction of error bound but also the opportunity of obtaining better insight into the systems.",

author = "M. Hasheminejad and J. Murata and K. Hirasawa",

year = "1994",

month = dec,

day = "1",

language = "English",

pages = "39--44",

note = "Proceedings of the Artificial Neural Networks in Engineering Conference (ANNIE'94) ; Conference date: 13-11-1994 Through 16-11-1994",

}

TY - CONF

T1 - System identification using neural network with parametric sigmoid function

AU - Hasheminejad, M.

AU - Murata, J.

AU - Hirasawa, K.

PY - 1994/12/1

Y1 - 1994/12/1

N2 - Nonlinear systems can be modeled by neural networks. However choice of suitable network architecture is the most important problem. And 'how to find the best activation function' is a persistent aspect of the architecture design. Here we have proposed a sigmoid function with one parameter which provides us not only the reduction of error bound but also the opportunity of obtaining better insight into the systems.

AB - Nonlinear systems can be modeled by neural networks. However choice of suitable network architecture is the most important problem. And 'how to find the best activation function' is a persistent aspect of the architecture design. Here we have proposed a sigmoid function with one parameter which provides us not only the reduction of error bound but also the opportunity of obtaining better insight into the systems.

UR - http://www.scopus.com/inward/record.url?scp=0028740890&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028740890&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0028740890

SP - 39

EP - 44

T2 - Proceedings of the Artificial Neural Networks in Engineering Conference (ANNIE'94)

Y2 - 13 November 1994 through 16 November 1994

ER -

System identification using neural network with parametric sigmoid function

Abstract

Conference

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this