Researchers Collaborate to Build Supercomputer that Simulates Human Brain
A team of researchers from Western Sydney University in Australia has partnered with tech giants Intel and Dell to create a massive supercomputer called DeepSouth. The goal of this project is to simulate neural networks at the scale of the human brain.
DeepSouth has the capability to emulate networks of spiking neurons at an astounding rate of 228 trillion synaptic operations per second, which is comparable to the estimated speed of the human brain. The announcement of this project took place at the NeuroEng Workshop hosted by Western Sydney’s International Centre for Neuromorphic Systems (ICNS), a renowned platform for experts in computational neuroscience.
Upon its completion in April next year, DeepSouth is expected to provide researchers with unprecedented insights into how the human brain processes information.
“Our understanding of how brains compute using neurons is hindered by our inability to simulate brain-like networks on a large scale,” said ICNS director and Western Sydney professor André van Schaik in a statement.
Efficient and Power-Efficient Computing
The researchers are not aiming for DeepSouth to become the most powerful conventional supercomputer globally. Instead, they are focused on simulating the brain’s network of neurons using a “neuromorphic system which mimics biological processes,” as stated in the press release.
This approach results in a more efficient and less power-hungry supercomputer, specifically designed to simulate synaptic activity in the human brain. In simple terms, neuromorphic computing involves performing numerous operations simultaneously while minimizing data movement, leading to significantly reduced energy consumption.
“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,” explained van Schaik. “Our system will change that.”
The research team aims to advance the understanding of the brain and develop brain-scale computing applications in various fields, including sensing, biomedical, robotics, space, and large-scale AI applications.
This technology could potentially lead to the development of advanced smart devices and enable AI models to operate with lower power consumption.
Other researchers are already enthusiastic about the potential of DeepSouth. Ralph Etienne-Cummings, a computer engineering professor at Johns Hopkins University, who was not involved in the project, told New Scientist, “At the end of the day, there are two types of researchers who will be interested in this — either those studying neuroscience or those who want to prototype new engineering solutions in the AI space. If you are trying to understand the brain, this will be the hardware to do it on.”
More on supercomputers: China May Have Secretly Built Two Exascale Supercomputers