Researchers in Australia are on the verge of completing the world's first brain-scale computer, named DeepSouth. The International Centre for Neuromorphic Systems (ICNS) in Sydney, in collaboration with Intel and Dell, is behind this groundbreaking project. Set to go online next year, DeepSouth is being constructed at Western Sydney University and is designed with unique hardware chips that implement spiking neural networks. These networks replicate the way synapses process information in the human brain. While there have been previous neuromorphic computers, DeepSouth is set to be the largest, capable of performing 228 trillion synaptic operations per second – a scale comparable to the estimated synaptic operations in the human brain.

DeepSouth stands out due to its focus on spiking neural networks, which are a departure from conventional computers. Spiking neural networks closely model the brain's synaptic processes, offering a new avenue for studying and understanding biological brains. Although DeepSouth may not surpass existing supercomputers in terms of raw power, its primary purpose is to advance the understanding of neuromorphic computing and biological brains. ICNS member and project lead Andre van Schaik emphasized the importance of DeepSouth in enhancing our knowledge of how brains function, stating, "We need this ability to better learn how brains work and how they do what they do so well."

Ralph Etienne-Cummings, a researcher from John Hopkins University not involved in the project, believes DeepSouth will significantly expedite scientific studies. He notes that researchers will be able to repeatedly test models of the brain, facilitating a deeper understanding. Etienne-Cummings envisions two main groups benefiting from DeepSouth: neuroscientists seeking to understand the intricacies of the brain and researchers in artificial intelligence (AI) looking to prototype new engineering solutions. According to him, DeepSouth will be the go-to hardware for those aiming to comprehend the complexities of the brain.

Moreover, DeepSouth has the potential to revolutionize energy efficiency in computing. Etienne-Cummings suggests that this supercomputer could pave the way for much higher energy efficiency in computing. By mimicking the brain's processes, DeepSouth may lead to more efficient AI processes compared to current models. This could have far-reaching implications for the field of artificial intelligence, offering more effective ways to undertake AI processes.

In terms of benefits, DeepSouth is expected to facilitate super-fast, large-scale parallel processing while consuming significantly less power. This capability could revolutionize the efficiency of computing processes. The scalability of DeepSouth is also highlighted as a crucial advantage. It allows for the addition of more hardware to create a larger system or scaling down for smaller, portable, or more cost-effective applications. This adaptability makes DeepSouth a versatile tool for various computing needs.

You might also be intersted in - Australian unions fight for WFH flexibility as companies shift towards pre-pandemic work setting