DeepSwarm: Optimising Convolutional Neural Networks using Swarm Intelligence

Edvinas Byla, Wei Pang

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

31 Citations (Scopus)

Abstract

In this paper we propose DeepSwarm, a novel neural architecture search (NAS) method based on Swarm Intelligence principles. At its core DeepSwarm uses Ant Colony Optimization (ACO) to generate ant population which uses the pheromone information to collectively search for the best neural architecture. Furthermore, by using local and global pheromone update rules our method ensures the balance between exploitation and exploration. On top of this, to make our method more efficient we combine progressive neural architecture search with weight reusability. Furthermore, due to the nature of ACO our method can incorporate heuristic information which can further speed up the search process. After systematic and extensive evaluation, we discover that on three different datasets (MNIST, Fashion-MNIST, and CIFAR-10) when compared to existing systems our proposed method demonstrates competitive performance. Finally, we open source DeepSwarm (https://github.com/Pattio/DeepSwarm) as a NAS library and hope it can be used by more deep learning researchers and practitioners.
Original languageEnglish
Title of host publicationAdvances in Computational Intelligence Systems. UKCI 2019
EditorsZhaojie Ju, Longzhi Yang, Chenguang Yang, Alexander Gegov, Dalin Zhou
PublisherSpringer
Pages119-130
Number of pages12
ISBN (Electronic)9783030299330
ISBN (Print)9783030299323
DOIs
Publication statusPublished - 30 Aug 2019

Publication series

NameAdvances in Intelligent Systems and Computing
Volume1043
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Keywords

  • Ant Colony Optimization
  • Neural Architecture Search

Fingerprint

Dive into the research topics of 'DeepSwarm: Optimising Convolutional Neural Networks using Swarm Intelligence'. Together they form a unique fingerprint.

Cite this