# DeepSwarm: Optimising Convolutional Neural Networks using Swarm Intelligence

arXiv: https://arxiv.org/abs/1905.07350 · HTML: https://mlsanity.com/paper/1905.07350/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 May 2019.

## Built on by (most cited first, 6 of 6)

- [ArchGym: An Open-Source Gymnasium for Machine Learning Assisted Architecture Design](https://mlsanity.com/paper/2306.08888/) (2023)
- [CONetV2: Efficient Auto-Channel Size Optimization for CNNs](https://mlsanity.com/paper/2110.06830/) (2021)
- [Exploring the Intersection between Neural Architecture Search and Continual Learning](https://mlsanity.com/paper/2206.05625/) (2022)
- [Neural Architecture Search using Particle Swarm and Ant Colony Optimization](https://mlsanity.com/paper/2403.03781/) (2024)
- [TS-ENAS:Two-Stage Evolution for Cell-based Network Architecture Search](https://mlsanity.com/paper/2310.09525/) (2023)
- [HiveNAS: Neural Architecture Search using Artificial Bee Colony Optimization](https://mlsanity.com/paper/2211.10250/) (2022)

## Abstract (arXiv)

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 as a NAS library and hope it can be used by more deep learning researchers and practitioners.