# Neural Architecture Search using Particle Swarm and Ant Colony Optimization

arXiv: https://arxiv.org/abs/2403.03781 · HTML: https://mlsanity.com/paper/2403.03781/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 26 references that are in the map.
- First posted on arXiv 6 Mar 2024.

## Builds on (most cited first, 7 of 7)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Auto-Keras: An Efficient Neural Architecture Search System](https://mlsanity.com/paper/1806.10282/) (2018)
- [DeepSwarm: Optimising Convolutional Neural Networks using Swarm Intelligence](https://mlsanity.com/paper/1905.07350/) (2019)
- [Autonomous Deep Learning: A Genetic DCNN Designer for Image Classification](https://mlsanity.com/paper/1807.00284/) (2018)

## Built on by (most cited first, 2 of 2)

- [Pheromone-based Learning of Optimal Reasoning Paths](https://mlsanity.com/paper/2501.19278/) (2025)
- [Evolutionary Architecture Search through Grammar-Based Sequence Alignment](https://mlsanity.com/paper/2512.04992/) (2025)

## Abstract (arXiv)

Neural network models have a number of hyperparameters that must be chosen along with their architecture. This can be a heavy burden on a novice user, choosing which architecture and what values to assign to parameters. In most cases, default hyperparameters and architectures are used. Significant improvements to model accuracy can be achieved through the evaluation of multiple architectures. A process known as Neural Architecture Search (NAS) may be applied to automatically evaluate a large number of such architectures. A system integrating open source tools for Neural Architecture Search (OpenNAS), in the classification of images, has been developed as part of this research. OpenNAS takes any dataset of grayscale, or RBG images, and generates Convolutional Neural Network (CNN) architectures based on a range of metaheuristics using either an AutoKeras, a transfer learning or a Swarm Intelligence (SI) approach. Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO) are used as the SI algorithms. Furthermore, models developed through such metaheuristics may be combined using stacking ensembles. In the context of this paper, we focus on training and optimizing CNNs using the Swarm Intelligence (SI) components of OpenNAS. Two major types of SI algorithms, namely PSO and ACO, are compared to see which is more effective in generating higher model accuracies. It is shown, with our experimental design, that the PSO algorithm performs better than ACO. The performance improvement of PSO is most notable with a more complex dataset. As a baseline, the performance of fine-tuned pre-trained models is also evaluated.