Researchers boost Artificial Intelligence (AI) with evolution

Cornell University researchers have successfully simulated 25,000 generations of evolution in an effort to determine why biological networks tend to be organized as modules.

According to Professor Jeff Clune, The research is expected to help evolve the field of artificial intelligence, allowing robot brains to acquire the “grace and cunning” of animals.

“From brains to gene regulatory networks, many biological entities are organized into modules – dense clusters of interconnected parts within a complex network,” he explained.

“For decades biologists have wanted to know why humans, bacteria and other organisms evolved in a modular fashion. Like engineers, nature builds things modularly by building and combining distinct parts, but that does not explain how such modularity evolved in the first place.”

Indeed, biologists Richard Dawkins, Günter P. Wagner and the late Stephen Jay Gould identified the question of modularity as central to the debate over “the evolution of complexity.”

For years, the prevailing assumption was simply that modules evolved because entities that were modular could respond to change more quickly, and therefore had an adaptive advantage over their non-modular competitors.

But that may not be enough to explain the origin of the phenomena. To be sure, the team discovered that evolution produces modules not because they produce more adaptable designs, but because modular designs have fewer and shorter network connections, which are costly to build and maintain.

As it turned out, it was enough to include a “cost of wiring” to make evolution favor modular architectures. To test the theory, the researchers simulated the evolution of networks with and without a cost for network connections.

“Once you add a cost for network connections, modules immediately appear. Without a cost, modules never form. The effect is quite dramatic,” says Clune.

The results could help explain the near-universal presence of modularity in biological networks as diverse as neural networks – such as animal brains – and vascular networks, gene regulatory networks, protein-protein interaction networks, metabolic networks and even human-constructed networks such as the Internet.

“Being able to evolve modularity will let us create more complex, sophisticated computational brains,” added Clune.