Machine Intelligence inspired by Slime


Abstract. Swarm intelligence refers to the capacity of biological systems to produce complex behaviour when many simple agents interact. This principle is ubiquitous in nature, from the smallest scale of bacteria and neurons, all the way to the evolution of ecosystems. Most intriguing is to observe their emergent properties, where the whole is greater than the sum of the parts, such as building structures together, synchronising in flight, or very efficient foraging. Natural computing is a field of computational methods where such behaviours in nature inspire simulations or are used directly to solve problems. In this talk I’d like to introduce an alternative perspective to artificial intelligence, one where the problem-solving skills are derived from the collaboration of agents and their collective intelligence.

Presented at the Imperial Lates: AI public outreach event. The event featured a silent disco collective dancing exercise (“SwarmDance”), an anti-facial recognition make-up workshop, and many more.

When: 14 Mar 2024, 19:30
Where: Imperial Lates: AI, Business School foyer, Imperial College London