ITP Techblog

Computer chips with brain-like functionality that could reduce global carbon emissions from computing have been developed by a team led by University of Canterbury Professor Simon Brown.

Together with doctoral students Josh Mallinson, Shota Shirai and Edoardo Galli, and postdoctoral fellows Susant Acharya and Saurabh Bose, he has published a paper in the peer-reviewed journal Science Advances, called Avalanches and criticality in self-organised nanoscale networks.

"The research shows the chips are based on self-organisation of nanoparticles - taking advantage of physical principles at unimaginably small scales, a hundred thousand times smaller than the thickness of a human hair, to make brain-like networks," a release from Canterbury University notes.

What that means in lay terms is the signals on the computer chips are similar to those that pass through the network of neurons in the brain. As the brain is good at processing information using small amounts of energy, it follows that the computer chips can process data using less energy.

The components of this new chip are at the atomic level and are so small they cannot be seen with the naked eye or conventional microscopes, and can only be seen in electron microscopes.

"Brain-like computing could enable "edge computing" and address the ever increasing energy consumption of computers," a release from Canterbury University notes.

An additional advantage is that it can potentially reduce the amount of data shared with companies such as Google and Facebook, thereby improving privacy.

"The research shows that this type of chip really does mimic the signalling behaviour of the brain. We were surprised at the extent to which the avalanches or cascades of voltage pulses on our chips replicate the avalanches of 'action potentials' that are observed in the brain. These are the signals that pass instructions from one 'neuron' to another, and so replicating them is an important step towards being able to make computer chips with brain-like functionality," Professor Brown says.

These chips might provide a different kind of artificial intelligence. By understanding the underlying fundamental physical processes, we believe we can design these chips and control their behaviour to do things like pattern or image recognition," he says.

Potential applications of on-chip pattern recognition technology can be found in retinal scans on cell phones, robotics, autonomous vehicles and biomedical devices.

Conscious of concerns about AI, the team is looking to work with social scientists to understand ethical considerations as they continue with their research.

You can read the research paper here.