Optimizing Artificial Neural Network for Functions Approximation Using Particle Swarm Optimization

Lina Zaghloul, Rawan Zaghloul, Mohammad Hamdan*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Artificial neural networks (ANN) are commonly used in function approximation as well as classification problems. This paper shows a configurable architecture of a simple feed forward neural network trained by particle swarm optimization (PSO) algorithm. PSO and ANN have several hyperparameters that have impact on the results of approximation. ANN parameters are the number of layers, number of neurons in each layer, and neuron activation functions. The hyperparameters of the PSO are the population size, the number of informants per particle, and the acceleration coefficients. Herein, this work comes to spot the light on how the PSO hyperparameters affect the ability of the algorithm to optimize ANNs weights in the function approximation task. This was examined and tested by generating multiple experiments on different types of input functions such as: cubic, linear, XOR problem. The results of the proposed method show the superiority of PSO compared to backpropagation in terms of MSE.

Original languageEnglish
Title of host publicationAdvances in Swarm Intelligence. ICSI 2021
EditorsYing Tan, Yuhui Shi
PublisherSpringer
Pages223-231
Number of pages9
ISBN (Electronic)9783030787431
ISBN (Print)9783030787424
DOIs
Publication statusPublished - 7 Jul 2021
Event12th International Conference on Advances in Swarm Intelligence 2021 - Virtual, Online
Duration: 17 Jul 202121 Jul 2021

Publication series

NameLecture Notes in Computer Science
Volume12689
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference12th International Conference on Advances in Swarm Intelligence 2021
Abbreviated titleICSI 2021
CityVirtual, Online
Period17/07/2121/07/21

Keywords

  • Artificial Neural Network (ANN)
  • Backpropagation
  • Function Approximation
  • Mean Square Error (MSE)
  • Particle Swarm Optimization (PSO)

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science

Fingerprint

Dive into the research topics of 'Optimizing Artificial Neural Network for Functions Approximation Using Particle Swarm Optimization'. Together they form a unique fingerprint.

Cite this