Cover Image

Calculation of hybrid multi-layered perceptron neural network output using matrix multiplication

After some studies on the HMLP neural network output equation, it was found out that parts of the equation resemble matrix multiplication operation. Therefore, an approach to calculate the output equation of the HMLP using matrix multiplication method was proposed. The proposed approach was simulate...

Full description

Saved in:
Bibliographic Details
Main Authors: Siti Maryam, Sharun, Mohd Yusoff, Mashor, Ehkan, Phaklen, Lee, Yee Ann
Format: Conference or Workshop Item
Language:English
Published: 2017
Subjects:
TK Electrical engineering. Electronics Nuclear engineering
Online Access:http://eprints.unisza.edu.my/1682/1/FH03-FRIT-17-08229.jpg
http://eprints.unisza.edu.my/1682/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-unisza-ir.1682
record_format eprints
spelling my-unisza-ir.16822020-11-19T07:18:28Z http://eprints.unisza.edu.my/1682/ Calculation of hybrid multi-layered perceptron neural network output using matrix multiplication Siti Maryam, Sharun Mohd Yusoff, Mashor Ehkan, Phaklen Lee, Yee Ann TK Electrical engineering. Electronics Nuclear engineering After some studies on the HMLP neural network output equation, it was found out that parts of the equation resemble matrix multiplication operation. Therefore, an approach to calculate the output equation of the HMLP using matrix multiplication method was proposed. The proposed approach was simulated and compared with another approach to calculate HMLP output using loops. The result proved that the output of the HMLP calculated using matrix multiplication method is the same as when being calculated using looping method. When comparing the processing time of both methods, the matrix multiplication method is faster than looping method for HMLP with more nodes. However, looping method calculated the output faster for HMLP with less nodes. This paper presents part of an ongoing study with the goal to develop an architecture for implementing the HMLP on FPGA 2017 Conference or Workshop Item NonPeerReviewed image en http://eprints.unisza.edu.my/1682/1/FH03-FRIT-17-08229.jpg Siti Maryam, Sharun and Mohd Yusoff, Mashor and Ehkan, Phaklen and Lee, Yee Ann (2017) Calculation of hybrid multi-layered perceptron neural network output using matrix multiplication. In: 3rd International Conference on Electronic Design, ICED 2016, 11- 12 August 2015, Phuket; Thailand.
institution Universiti Sultan Zainal Abidin
building UNISZA Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Sultan Zainal Abidin
content_source UNISZA Institutional Repository
url_provider https://eprints.unisza.edu.my/
language English
topic TK Electrical engineering. Electronics Nuclear engineering
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
Siti Maryam, Sharun
Mohd Yusoff, Mashor
Ehkan, Phaklen
Lee, Yee Ann
Calculation of hybrid multi-layered perceptron neural network output using matrix multiplication
description After some studies on the HMLP neural network output equation, it was found out that parts of the equation resemble matrix multiplication operation. Therefore, an approach to calculate the output equation of the HMLP using matrix multiplication method was proposed. The proposed approach was simulated and compared with another approach to calculate HMLP output using loops. The result proved that the output of the HMLP calculated using matrix multiplication method is the same as when being calculated using looping method. When comparing the processing time of both methods, the matrix multiplication method is faster than looping method for HMLP with more nodes. However, looping method calculated the output faster for HMLP with less nodes. This paper presents part of an ongoing study with the goal to develop an architecture for implementing the HMLP on FPGA
format Conference or Workshop Item
author Siti Maryam, Sharun
Mohd Yusoff, Mashor
Ehkan, Phaklen
Lee, Yee Ann
author_facet Siti Maryam, Sharun
Mohd Yusoff, Mashor
Ehkan, Phaklen
Lee, Yee Ann
author_sort Siti Maryam, Sharun
title Calculation of hybrid multi-layered perceptron neural network output using matrix multiplication
title_short Calculation of hybrid multi-layered perceptron neural network output using matrix multiplication
title_full Calculation of hybrid multi-layered perceptron neural network output using matrix multiplication
title_fullStr Calculation of hybrid multi-layered perceptron neural network output using matrix multiplication
title_full_unstemmed Calculation of hybrid multi-layered perceptron neural network output using matrix multiplication
title_sort calculation of hybrid multi-layered perceptron neural network output using matrix multiplication
publishDate 2017
url http://eprints.unisza.edu.my/1682/1/FH03-FRIT-17-08229.jpg
http://eprints.unisza.edu.my/1682/
_version_ 1684657736638267392
score 13.211869

Similar Items