Decoret / Shutterstock" src="https://s.yimg.com/ny/api/res/1.2/hvAoLyRd9nfsqQ3mfhaVqQ-/YXBwaWQ9aGlnaGxhbmRlcjt3PTk2MDtoPTU4NQ-/https://media.zenfs.com/en/the_conversation_464/2f69064fd728adfb 03aa9e42b3698b69″ data-src= "https://s.yimg.com/ny/api/res/1.2/hvAoLyRd9nfsqQ3mfhaVqQ-/YXBwaWQ9aGlnaGxhbmRlcjt3PTk2MDtoPTU4NQ-/https://media.zenfs.com/en/the_conversation_464/2f69064fd728adfb03aa9 e42b3698b69″/>
A supercomputer set to come online in April 2024 will rival the estimated speed of operations in the human brain, according to researchers in Australia. The machine, called DeepSouth, can perform 228 trillion operations per second.
It is the world's first supercomputer that can simulate networks of neurons and synapses (key biological structures that make up our nervous system) on the scale of the human brain.
DeepSouth belongs to an approach known as neuromorphic computing, which aims to mimic the biological processes of the human brain. It will be led from the International Center for Neuromorphic Systems at Western Sydney University.
Our brain is the most amazing computing machine we know. By distributing its computing power among billions of tiny units (neurons) interacting through trillions of connections (synapses), the brain can rival the world's most powerful supercomputers while requiring only the same power as the light bulb of a refrigerator lamp.
Supercomputers, on the other hand, generally take up a lot of space and require large amounts of electrical energy to function. The world's most powerful supercomputer, the Hewlett Packard Enterprise Frontier, can perform just over a trillion operations per second. It covers 680 square meters (7,300 square feet) and requires 22.7 megawatts (MW) to run.
Our brains can perform the same number of operations per second with only 20 watts of power, while weighing only 1.3 to 1.4 kg. Neuromorphic computing aims, among other things, to unlock the secrets of this astonishing efficiency.
Transistors at the limits
On June 30, 1945, mathematician and physicist John von Neumann described the design of a new machine, the Electronic Discrete Variable Automatic Computer (Edvac). This effectively defined the modern electronic computer as we know it.
My smartphone, the laptop I use to write this article, and the world's most powerful supercomputer all share the same fundamental structure that Von Neumann introduced nearly 80 years ago. These all have different processing and memory units, where data and instructions are stored in memory and calculated by a processor.
The story continues
For decades, the number of transistors on a microchip doubled approximately every two years, an observation known as Moore's law. This allowed us to have smaller and cheaper computers.
However, transistor sizes are now approaching the atomic scale. At these small sizes, excessive heat generation is a problem, as is a phenomenon called quantum tunneling, which disrupts the operation of the transistors. This slows down and will eventually halt the miniaturization of the transistors.
To overcome this problem, scientists are exploring new approaches to computing, starting with the powerful computer we all have hidden in our heads: the human brain. Our brains do not work according to John von Neumann's computer model. They do not have separate computing and memory areas.
Instead, they work by connecting billions of nerve cells that communicate information in the form of electrical impulses. Information can be passed from one neuron to the next through a junction called a synapse. The organization of neurons and synapses in the brain is flexible, scalable and efficient.
So in the brain - and unlike in a computer - memory and computing power are controlled by the same neurons and synapses. Since the late 1980s, scientists have been studying this model with the intention of importing it into the computing world.
Imitation of life
Neuromorphic computers are based on complex networks of simple, basic processors (which function like the neurons and synapses of the brain). The big advantage of this is that these machines are inherently "parallel".
This means that, as with neurons and synapses, virtually all processors in a computer can potentially work simultaneously and communicate in tandem.
In addition, because the calculations performed by individual neurons and synapses are very simple compared to traditional computers, the energy consumption is orders of magnitude smaller. Although neurons are sometimes thought of as processing units and synapses as memory units, they contribute to both processing and storage. In other words, the data is already where the calculation requires it.
This speeds up brain computing in general because there is no separation between memory and processor, which causes a slowdown in classical (von Neumann) machines. But it also avoids the need to perform a specific task, namely accessing data from a main memory component, as happens in conventional computer systems and which consume a significant amount of energy.
The principles we have just described are the main source of inspiration for DeepSouth. This is not the only neuromorphic system currently active. Worth mentioning is the Human Brain Project (HBP), funded by an EU initiative. The HBP was operational from 2013 to 2023 and led to BrainScaleS, a machine in Heidelberg, Germany, that mimics the way neurons and synapses work.
BrainScaleS can simulate the way neurons 'spike', the way an electrical impulse travels along a neuron in our brain. This would make BrainScaleS an ideal candidate to investigate the mechanics of cognitive processes and, in the future, mechanisms underlying serious neurological and neurodegenerative diseases.
Because they are designed to mimic real brains, neuromorphic computers could be the beginning of a turning point. They provide sustainable and affordable computing power and enable researchers to evaluate models of neurological systems, making them an ideal platform for a range of applications. They have the potential to both advance our understanding of the brain and provide new approaches to artificial intelligence.
This article is republished from The Conversation under a Creative Commons license. Read the original article.
