Parameters optimization of deep learning models using Particle swarm optimization

Basheer Qolomany, Majdi Maabreh, Ala Al-Fuqaha, Ajay Gupta, Driss Benhaddou

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

38 Scopus citations

Abstract

Deep learning has been successfully applied in several fields such as machine translation, manufacturing, and pattern recognition. However, successful application of deep learning depends upon appropriately setting its parameters to achieve high-quality results. The number of hidden layers and the number of neurons in each layer of a deep machine learning network are two key parameters, which have main influence on the performance of the algorithm. Manual parameter setting and grid search approaches somewhat ease the users' tasks in setting these important parameters. Nonetheless, these two techniques can be very time-consuming. In this paper, we show that the Particle swarm optimization (PSO) technique holds great potential to optimize parameter settings and thus saves valuable computational resources during the tuning process of deep learning models. Specifically, we use a dataset collected from a Wi-Fi campus network to train deep learning models to predict the number of occupants and their locations. Our preliminary experiments indicate that PSO provides an efficient approach for tuning the optimal number of hidden layers and the number of neurons in each layer of the deep learning algorithm when compared to the grid search method. Our experiments illustrate that the exploration process of the landscape of configurations to find the optimal parameters is decreased by 77 % - 85%. In fact, the PSO yields even better accuracy results.

Original languageEnglish (US)
Title of host publication2017 13th International Wireless Communications and Mobile Computing Conference, IWCMC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1285-1290
Number of pages6
ISBN (Electronic)9781509043729
DOIs
StatePublished - Jul 19 2017
Externally publishedYes
Event13th IEEE International Wireless Communications and Mobile Computing Conference, IWCMC 2017 - Valencia, Spain
Duration: Jun 26 2017Jun 30 2017

Publication series

Name2017 13th International Wireless Communications and Mobile Computing Conference, IWCMC 2017

Conference

Conference13th IEEE International Wireless Communications and Mobile Computing Conference, IWCMC 2017
CountrySpain
CityValencia
Period6/26/176/30/17

Keywords

  • Deep machine learning
  • Parameter optimization
  • Particle swarm optimization
  • Smart building services

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Signal Processing

Fingerprint Dive into the research topics of 'Parameters optimization of deep learning models using Particle swarm optimization'. Together they form a unique fingerprint.

Cite this