Understanding Biological Networks Systems Can Help Develop Better AI
Understanding the hierarchical structure of biological networks like human brain — a network of neurons — could be useful in creating more complex, intelligent computational brains in the fields of artificial intelligence and robotics, says a study.
Like large businesses, many biological networks are hierarchically organised, such as gene, protein, neural, and metabolic networks. This means they have separate units that can each be repeatedly divided into smaller and smaller subunits.
To understand as to why biological networks evolve to be hierarchical, researchers from the University of Wyoming and the French Institute for Research in Computer Science and Automation (INRIA) simulated the evolution of computational brain models, known as artificial neural networks, both with and without a cost for network connections.
They found that hierarchy evolves not because it produces more efficient networks, but instead because hierarchically wired networks have fewer connections.
This is because connections in biological networks are expensive – they have to be built, housed, maintained, etc. – and there is therefore an evolutionary pressure to reduce the number of connections, said the study published recently in the journal PLOS Computational Biology.
“The findings not only explain why biological networks are hierarchical, they might also give an explanation for why many human-made systems such as the internet and road systems are also hierarchical,” said Henok S. Mengistu, who led the research.
“The next step is to harness and combine this knowledge to evolve large-scale, structurally organised networks in the hopes of creating better artificial intelligence and increasing our understanding of the evolution of animal intelligence, including our own,” said study co-author Joost Huizinga of Wyoming.