DeepSwarm: Optimising Convolutional Neural Networks using Swarm Intelligence

Understand

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.