The efficiency of our brains in terms of energy consumption is truly remarkable.
With a mere 20 watts of power, the human brain exhibits the ability to process the equivalent of an exaflop — translating to a billion-billion mathematical operations per second.
Presently, Australian researchers are constructing the world’s inaugural supercomputer designed to simulate networks on this brain-scale magnitude.
Western Sydney University is currently in the process of developing a supercomputer named DeepSouth.
Upon its launch next year, it will have the capacity for 228 trillion synaptic operations per second, comparable to the estimated rate of operations in the human brain.
The objective is to gain a deeper understanding of how brains efficiently utilize minimal power to process vast amounts of information.
If researchers successfully unravel this, they might eventually develop a cyborg brain that surpasses our current capabilities. This breakthrough could potentially revolutionize our comprehension of brain functionality.
“Progress in our understanding of how brains compute using neurons is hampered by our inability to simulate brain-like networks at scale,” said André van Schaik, a director at Western Sydney University’s International Centre for Neuromorphic Systems.
“Simulating spiking neural networks on standard computers using Graphics Processing Units and multicore Central Processing Units is just too slow and power intensive,” he added. “Our system will change that.”
Ralph Etienne-Cummings at Johns Hopkins University, Baltimore, who is not involved in the work, told New Scientist that DeepSouth will be a game changer for the study of neuroscience.
“If you are trying to understand the brain this will be the hardware to do it on,” he said.
Etienne-Cummings mentioned that the technology will attract two primary categories of researchers: those focused on neuroscience studies and those aiming to prototype innovative engineering solutions in the AI domain.
DeepSouth represents just one among numerous research projects striving to develop a machine that can match the capabilities of the human brain.
Other researchers are addressing the same challenge by developing “biological computers” fueled by actual brain cells.
This piece was initially featured on Business Insider.