Artificial intelligence systems that are designed with a biologically inspired architecture can simulate human brain

activity before ever being trained on any data, according to new research from Johns Hopkins University.

The findings, published in Nature Machine Intelligence, challenge conventional approaches to building AI by prioritizing

architectural design over the type of deep learning and training that takes months, costs billions of dollars and

requires thousands of megawatts of energy.

"The way that the AI field is moving right now is to throw a bunch of data at the models and build compute resources the

size of small cities. That requires spending hundreds of billions of dollars. Meanwhile, humans learn to see using very

little data," said lead author Mick Bonner, assistant professor of cognitive science at Johns Hopkins University.

"Evolution may have converged on this design for a good reason. Our work suggests that architectural designs that are

more brain-like put the AI systems in a very advantageous starting point."

How researchers tested brain-like AI

Bonner and a team of scientists focused on three classes of network designs that AI developers commonly use as

blueprints for building their AI systems: transformers, fully connected networks, and convolutional networks.

The scientists repeatedly modified the three blueprints, or the AI architectures, to build dozens of unique artificial

neural networks. Then, they exposed these new and untrained AI networks to images of objects, people, and animals and

compared the models' responses to the brain activity of humans and primates exposed to the same images.

When transformers and fully connected networks were modified by giving them many more artificial neurons, they showed

little change. Tweaking the architectures of convolutional neural networks in a similar way, however, allowed the

researchers to generate activity patterns in the AI that better simulated patterns in the human brain.

The untrained convolutional neural networks rivaled conventional AI systems, which generally are exposed to millions or

billions of images during training, the researchers said, suggesting that the architecture plays a more important role

than researchers previously realized.

Implications for future AI development

"If training on massive data is really the crucial factor, then there should be no way of getting to brain-like AI

systems through architectural modifications alone," Bonner said. "This means that by starting with the right blueprint,

and perhaps incorporating other insights from biology, we may be able to dramatically accelerate learning in AI

systems."