DeepSouth aims to be operational by April 2024.
Numerous science fiction films depict computers mirroring human intelligence, often surpassing human capabilities. These futuristic portrayals showcase machines that emulate human minds, raising questions about the potential consequences and ethical implications of advanced artificial intelligence. The once-fictional scenario is poised to transition into reality with the imminent activation of a supercomputer in Australia next year. This groundbreaking system is designed to simulate human brain synapses at full scale, aiming to unravel the mysteries of how our brains efficiently process vast amounts of information with minimal power consumption.
The machine, known as DeepSouth, a brain-inspired supercomputer crafted by researchers at the International Centre for Neuromorphic Systems (ICNS) at Western Sydney University in Sydney, boasts spiking neural networks on its chips. This innovative technology, partnered with Intel and Dell, aims to unlock the secrets of how our brains handle information with surprising efficiency.
As per a release by the Western Sydney University, DeepSouth uses a neuromorphic system that mimics biological processes, using hardware to efficiently emulate large networks of spiking neurons at 228 trillion synaptic operations per second, rivaling the estimated rate of operations in the human brain.
“DeepSouth stands apart from other supercomputers as it is purpose-built to operate like networks of neurons, requiring less power and enabling greater efficiencies. This contrasts with supercomputers optimised for more traditional computing loads, which are power hungry,” said ICNS Director, Professor Andre van Schaik.
“Progress in our understanding of how brains compute using neurons is hampered by our inability to simulate brain-like networks at scale. Simulating spiking neural networks on standard computers using Graphics Processing Units (GPUs) and multicore Central Processing Units (CPUs) is just too slow and power-intensive. Our system will change that,” the professor said.
“This platform will progress our understanding of the brain and develop brain-scale computing applications in diverse fields, including sensing, biomedical, robotics, space, and large-scale AI applications.”