University of Tasmania
Browse

File(s) under permanent embargo

A machine learning approach for modeling and its applications

conference contribution
posted on 2023-05-23, 08:17 authored by Shuxiang XuShuxiang Xu, Liu, Y, Byeong KangByeong Kang, Gao, W
This paper proposes a new learning algorithm for Higher Order Neural Networks for the purpose of modelling and applies it in three benchmark problems. Higher Order Neural Networks (HONNs) are Artificial Neural Networks (ANNs) in which the net input to a computational neuron is a weighted sum of its inputs and products of its inputs (rather than just a weighted sum of its inputs as in traditional ANNs). It was well known that HONNs can implement invariant pattern recognition. The new learning algorithm proposed is an Extreme Learning Machine (ELM) algorithm. ELM randomly chooses hidden neurons and analytically determines the output weights. With ELM algorithm only the connection weights between hidden layer and output layer are adjusted. This paper proposes an ELM algorithm for HONN models and applies it in an image processing problem, a medical problem, and an energy efficiency problem. The experimental results demonstrate the advantages of HONN models with the ELM algorithm in such aspects as significantly faster learning and improved generalization abilities (in comparison with standard HONN and traditional ANN models).

History

Publication title

Proceedings of the European Modeling and Simulation Symposium

Editors

A Bruzzone, E Jimenez, F Longo, and Y Merkuryev

Pagination

659-663

ISBN

978-88-97999-16-4

Department/School

School of Information and Communication Technology

Publisher

EMSS

Place of publication

Greece

Event title

European Modeling and Simulation Symposium

Event Venue

Athens, Greece

Date of Event (Start Date)

2013-09-25

Date of Event (End Date)

2013-09-27

Rights statement

Copyright 2013 Dime Università di Genova

Repository Status

  • Restricted

Socio-economic Objectives

Information systems, technologies and services not elsewhere classified

Usage metrics

    University Of Tasmania

    Categories

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC