A model of perceptron learning with a hidden layer for engineering design

Shih-Lin Hung; H. Adeli

doi:10.1016/0925-2312(91)90016-5

A model of perceptron learning with a hidden layer for engineering design

Shih-Lin Hung^*, H. Adeli

^*Corresponding author for this work

Department of Civil Engineering

Research output: Contribution to journal › Article › peer-review

27 Scopus citations

Abstract

A model of machine learning in engineering design, called PERHID, is presented based on the concept of perceptron learning algorithm with a two-layer neural network. PERHID has been constructed by combining the perceptron with a single-layer AND neural net. The problem of structural design is cast in a form that can be described by a two-layer neural network. Some results from PERHID learning model are presented in tabular form. The paper is concluded by a comparison of the learning by the previously developed single-layer perceptron and PERHID.

Original language	English
Pages (from-to)	3-14
Number of pages	12
Journal	Neurocomputing
Volume	3
Issue number	1
DOIs	https://doi.org/10.1016/0925-2312(91)90016-5
State	Published - 1 Jan 1991

Keywords

Artificial intelligence
design
machine learning
neural network
perceptron

Access to Document

10.1016/0925-2312(91)90016-5

Cite this

@article{c5ef311c00604f23984168f065ea8dda,

title = "A model of perceptron learning with a hidden layer for engineering design",

abstract = "A model of machine learning in engineering design, called PERHID, is presented based on the concept of perceptron learning algorithm with a two-layer neural network. PERHID has been constructed by combining the perceptron with a single-layer AND neural net. The problem of structural design is cast in a form that can be described by a two-layer neural network. Some results from PERHID learning model are presented in tabular form. The paper is concluded by a comparison of the learning by the previously developed single-layer perceptron and PERHID.",

keywords = "Artificial intelligence, design, machine learning, neural network, perceptron",

author = "Shih-Lin Hung and H. Adeli",

year = "1991",

month = jan,

day = "1",

doi = "10.1016/0925-2312(91)90016-5",

language = "English",

volume = "3",

pages = "3--14",

journal = "Neurocomputing",

issn = "0925-2312",

publisher = "Elsevier",

number = "1",

}

TY - JOUR

T1 - A model of perceptron learning with a hidden layer for engineering design

AU - Hung, Shih-Lin

AU - Adeli, H.

PY - 1991/1/1

Y1 - 1991/1/1

N2 - A model of machine learning in engineering design, called PERHID, is presented based on the concept of perceptron learning algorithm with a two-layer neural network. PERHID has been constructed by combining the perceptron with a single-layer AND neural net. The problem of structural design is cast in a form that can be described by a two-layer neural network. Some results from PERHID learning model are presented in tabular form. The paper is concluded by a comparison of the learning by the previously developed single-layer perceptron and PERHID.

AB - A model of machine learning in engineering design, called PERHID, is presented based on the concept of perceptron learning algorithm with a two-layer neural network. PERHID has been constructed by combining the perceptron with a single-layer AND neural net. The problem of structural design is cast in a form that can be described by a two-layer neural network. Some results from PERHID learning model are presented in tabular form. The paper is concluded by a comparison of the learning by the previously developed single-layer perceptron and PERHID.

KW - Artificial intelligence

KW - design

KW - machine learning

KW - neural network

KW - perceptron

UR - http://www.scopus.com/inward/record.url?scp=0026203882&partnerID=8YFLogxK

U2 - 10.1016/0925-2312(91)90016-5

DO - 10.1016/0925-2312(91)90016-5

M3 - Article

AN - SCOPUS:0026203882

SN - 0925-2312

VL - 3

SP - 3

EP - 14

JO - Neurocomputing

JF - Neurocomputing

IS - 1

ER -

A model of perceptron learning with a hidden layer for engineering design

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this