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

arXiv: https://arxiv.org/abs/1803.06492 · HTML: https://mlsanity.com/paper/1803.06492/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2018.

## Built on by (most cited first, 7 of 7)

- [An algorithmic framework for the optimization of deep neural networks architectures and hyperparameters](https://mlsanity.com/paper/2303.12797/) (2023)
- [PSO-Convolutional Neural Networks with Heterogeneous Learning Rate](https://mlsanity.com/paper/2205.10456/) (2022)
- [Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search](https://mlsanity.com/paper/2210.14016/) (2022)
- [AgentForge: A Flexible Low-Code Platform for Reinforcement Learning Agent Design](https://mlsanity.com/paper/2410.19528/) (2024)
- [Explaining Deep Convolutional Neural Networks for Image Classification by Evolving Local Interpretable Model-agnostic Explanations](https://mlsanity.com/paper/2211.15143/) (2022)
- [An Efficient Evolutionary Deep Learning Framework Based on Multi-source Transfer Learning to Evolve Deep Convolutional Neural Networks](https://mlsanity.com/paper/2212.03942/) (2022)
- [Artificial Bee Colony optimization of Deep Convolutional Neural Networks in the context of Biomedical Imaging](https://mlsanity.com/paper/2402.15246/) (2024)

## Abstract (arXiv)

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.