The DeepSouth supercomputer closely mimics the ingenuity of the human brain

The DeepSouth supercomputer closely mimics the ingenuity of the human brain

Performing hundreds of billions of calculations per second, while consuming minimal energy, is what the brain is capable of. The DeepSouth supercomputer is inspired by it to be able to accelerate the development of technologies, especially artificial intelligence.

This will interest you too

[EN VIDÉO] Interview: How is a quantum computer different? The quantum world is fascinating: on this scale, for example, things can…

AI algorithms know how to fool us thanks to massive probability calculations, but they do not think or function at all like our brains do. To simulate real neural networks, inspired by brainbrainresearchers fromNeural Systems International ICNS at the University of Western Sydney in Australia has unveiled the neural supercomputer Deep South. It will be activated from April 2024 and will be able to process 228 trillion entangled operations per second.

For its part, the human brain can calculate the equivalent of an exaflop (a billion billion floating-point operations performed in one second) of arithmetic operations per second and it only takes 20 minutes. whatswhats toenergyenergy To achieve this. Reproducing this power with less consumption is exactly what DeepSouth is designed to do.

Mimic the brain to consume less

With this computing power, the supercomputer should make it possible to speed up the processing of data around itApplicationsApplications Such as biomedicine, robotics, space research and artificial intelligence. However, its operation would be in contrast to current supercomputers, which are slow and power-hungry when simulating neural networks using graphics processing units (GPUs) and other multi-core chips.

READ  Google: What is this new security standard that will be imposed on you on November 9?

The name DeepSouph is a winkeyeeye For the TrueNorth supercomputerIBMIBM Which aims to build a machine capable of simulating large neural networks and DeepBlue, which was the first computer to defeat a human at chess. The great thing about DeepSouth is that it is scalable as well. It will therefore be possible to adapt and reconfigure them to increase or decrease their capabilities as required. If DeepSouth fulfills scientists’ expectations, by developing and miniaturizing itself, this kind of technology could further accelerate the development of artificial intelligence, while greatly reducing energy consumption.

Leave a Reply

Your email address will not be published. Required fields are marked *