Wang 2018 Evolving deep convolutional neural networks by variable-length.pdf (1.19 MB)

Evolving Deep Convolutional Neural Networks by Variable-Length Particle Swarm Optimization for Image Classification

Download (1.19 MB)
conference contribution
posted on 23.03.2021, 22:39 by Bin Wang, Y Sun, Bing Xue, Mengjie Zhang
© 2018 IEEE. Convolutional neural networks (CNNs) are one of the most effective deep learning methods to solve image classification problems, but the best architecture of a CNN to solve a specific problem can be extremely complicated and hard to design. This paper focuses on utilising Particle Swarm Optimisation (PSO) to automatically search for the optimal architecture of CNNs without any manual work involved. In order to achieve the goal, three improvements are made based on traditional PSO. First, a novel encoding strategy inspired by computer networks which empowers particle vectors to easily encode CNN layers is proposed; Second, in order to allow the proposed method to learn variable-length CNN architectures, a Disabled layer is designed to hide some dimensions of the particle vector to achieve variable-length particles; Third, since the learning process on large data is slow, partial datasets are randomly picked for the evaluation to dramatically speed it up. The proposed algorithm is examined and compared with 12 existing algorithms including the state-of-art methods on three widely used image classification benchmark datasets. The experimental results show that the proposed algorithm is a strong competitor to the state-of-art algorithms in terms of classification error. This is the first work using PSO for automatically evolving the architectures of CNNs. © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

History

Preferred citation

Wang, B., Sun, Y., Xue, B. & Zhang, M. (2018, September). Evolving Deep Convolutional Neural Networks by Variable-Length Particle Swarm Optimization for Image Classification. In 2018 IEEE Congress on Evolutionary Computation, CEC 2018 - Proceedings 2018 IEEE Congress on Evolutionary Computation (CEC), Rio de Janeiro, BRAZIL (00 pp. 1514-1521). IEEE. https://doi.org/10.1109/CEC.2018.8477735

Conference name

2018 IEEE Congress on Evolutionary Computation (CEC)

Conference Place

Rio de Janeiro, BRAZIL

Conference start date

08/07/2018

Conference finish date

13/07/2018

Title of proceedings

2018 IEEE Congress on Evolutionary Computation, CEC 2018 - Proceedings

Volume

00

Series

IEEE Congress on Evolutionary Computation

Contribution type

Published Paper

Publication or Presentation Year

28/09/2018

Pagination

1514-1521

Publisher

IEEE

Publication status

Published