Performance Evaluation of Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF)

Aminu Musa; Farouq Aliyu

doi:10.1109/NigeriaComputConf45974.2019.8949669

Performance Evaluation of Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF)

Aminu Musa, Farouq Aliyu

Center of Excellence in Development of Non-Profit Organizations

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

The importance of character recognition cannot be overemphasized. It finds applications in many automated systems. In most cases, these applications require high precision (e.g. automatic grading system, document digitization, license plate recognition systems, e.t.c) as well as low resource overhead. However, these are conflicting requirements, because the more the precision required, the more computation needed hence the more increase in resource overhead. In the research, two classification algorithms in Artificial Neural Networks (ANN): Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF) were applied to hand-written digit recognition and their performance is investigated. The duo was compared in terms of resources required for training and accuracy. It is found that MLP-NN is much faster to train (5.5min) compared to RBF (50.0min). However, during testing, it is found that both have an accuracy of ≈ 95%.

Original language	English
Title of host publication	2019 2nd International Conference of the IEEE Nigeria Computer Chapter, NigeriaComputConf 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728107134
DOIs	https://doi.org/10.1109/NigeriaComputConf45974.2019.8949669
State	Published - Oct 2019

Publication series

Name	2019 2nd International Conference of the IEEE Nigeria Computer Chapter, NigeriaComputConf 2019

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

Artificial Neural Networks
Levenberg-Marquardt
MATLAB NN Toolbox
Multi-layer Perceptron
Radial Basis Function

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Computer Science Applications
Information Systems and Management
Safety, Risk, Reliability and Quality
Control and Optimization

Access to Document

10.1109/NigeriaComputConf45974.2019.8949669

Cite this

Musa, A., & Aliyu, F. (2019). Performance Evaluation of Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF). In 2019 2nd International Conference of the IEEE Nigeria Computer Chapter, NigeriaComputConf 2019 Article 8949669 (2019 2nd International Conference of the IEEE Nigeria Computer Chapter, NigeriaComputConf 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NigeriaComputConf45974.2019.8949669

Musa, Aminu ; Aliyu, Farouq. / Performance Evaluation of Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF). 2019 2nd International Conference of the IEEE Nigeria Computer Chapter, NigeriaComputConf 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (2019 2nd International Conference of the IEEE Nigeria Computer Chapter, NigeriaComputConf 2019).

@inproceedings{c21680c7a56b45bda20b8411dcd5988b,

title = "Performance Evaluation of Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF)",

abstract = "The importance of character recognition cannot be overemphasized. It finds applications in many automated systems. In most cases, these applications require high precision (e.g. automatic grading system, document digitization, license plate recognition systems, e.t.c) as well as low resource overhead. However, these are conflicting requirements, because the more the precision required, the more computation needed hence the more increase in resource overhead. In the research, two classification algorithms in Artificial Neural Networks (ANN): Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF) were applied to hand-written digit recognition and their performance is investigated. The duo was compared in terms of resources required for training and accuracy. It is found that MLP-NN is much faster to train (5.5min) compared to RBF (50.0min). However, during testing, it is found that both have an accuracy of ≈ 95\%.",

keywords = "Artificial Neural Networks, Levenberg-Marquardt, MATLAB NN Toolbox, Multi-layer Perceptron, Radial Basis Function",

author = "Aminu Musa and Farouq Aliyu",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.",

year = "2019",

month = oct,

doi = "10.1109/NigeriaComputConf45974.2019.8949669",

language = "English",

series = "2019 2nd International Conference of the IEEE Nigeria Computer Chapter, NigeriaComputConf 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2019 2nd International Conference of the IEEE Nigeria Computer Chapter, NigeriaComputConf 2019",

address = "United States",

}

Musa, A & Aliyu, F 2019, Performance Evaluation of Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF). in 2019 2nd International Conference of the IEEE Nigeria Computer Chapter, NigeriaComputConf 2019., 8949669, 2019 2nd International Conference of the IEEE Nigeria Computer Chapter, NigeriaComputConf 2019, Institute of Electrical and Electronics Engineers Inc. https://doi.org/10.1109/NigeriaComputConf45974.2019.8949669

Performance Evaluation of Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF). / Musa, Aminu; Aliyu, Farouq.
2019 2nd International Conference of the IEEE Nigeria Computer Chapter, NigeriaComputConf 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8949669 (2019 2nd International Conference of the IEEE Nigeria Computer Chapter, NigeriaComputConf 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Performance Evaluation of Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF)

AU - Musa, Aminu

AU - Aliyu, Farouq

PY - 2019/10

Y1 - 2019/10

N2 - The importance of character recognition cannot be overemphasized. It finds applications in many automated systems. In most cases, these applications require high precision (e.g. automatic grading system, document digitization, license plate recognition systems, e.t.c) as well as low resource overhead. However, these are conflicting requirements, because the more the precision required, the more computation needed hence the more increase in resource overhead. In the research, two classification algorithms in Artificial Neural Networks (ANN): Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF) were applied to hand-written digit recognition and their performance is investigated. The duo was compared in terms of resources required for training and accuracy. It is found that MLP-NN is much faster to train (5.5min) compared to RBF (50.0min). However, during testing, it is found that both have an accuracy of ≈ 95%.

AB - The importance of character recognition cannot be overemphasized. It finds applications in many automated systems. In most cases, these applications require high precision (e.g. automatic grading system, document digitization, license plate recognition systems, e.t.c) as well as low resource overhead. However, these are conflicting requirements, because the more the precision required, the more computation needed hence the more increase in resource overhead. In the research, two classification algorithms in Artificial Neural Networks (ANN): Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF) were applied to hand-written digit recognition and their performance is investigated. The duo was compared in terms of resources required for training and accuracy. It is found that MLP-NN is much faster to train (5.5min) compared to RBF (50.0min). However, during testing, it is found that both have an accuracy of ≈ 95%.

KW - Artificial Neural Networks

KW - Levenberg-Marquardt

KW - MATLAB NN Toolbox

KW - Multi-layer Perceptron

KW - Radial Basis Function

UR - https://www.scopus.com/pages/publications/85078701154

U2 - 10.1109/NigeriaComputConf45974.2019.8949669

DO - 10.1109/NigeriaComputConf45974.2019.8949669

M3 - Conference contribution

AN - SCOPUS:85078701154

T3 - 2019 2nd International Conference of the IEEE Nigeria Computer Chapter, NigeriaComputConf 2019

BT - 2019 2nd International Conference of the IEEE Nigeria Computer Chapter, NigeriaComputConf 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Musa A, Aliyu F. Performance Evaluation of Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF). In 2019 2nd International Conference of the IEEE Nigeria Computer Chapter, NigeriaComputConf 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8949669. (2019 2nd International Conference of the IEEE Nigeria Computer Chapter, NigeriaComputConf 2019). doi: 10.1109/NigeriaComputConf45974.2019.8949669

Performance Evaluation of Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF)

Abstract

Publication series

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this