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.
CITATION STYLE
Byla, E., & Pang, W. (2020). DeepSwarm: Optimising Convolutional Neural Networks Using Swarm Intelligence. In Advances in Intelligent Systems and Computing (Vol. 1043, pp. 119–130). Springer Verlag. https://doi.org/10.1007/978-3-030-29933-0_10
Mendeley helps you to discover research relevant for your work.