Intel introduces a new neuromorphic system that mimics the human brain: equivalent to the calculation of 8 million neurons | LetsCompareOnline
Intel introduces a new neuromorphic system that mimics the human brain: equivalent to the calculation of 8 million neurons Intel introduces a new neuromorphic system that mimics the human brain: equivalent to the calculation of 8 million neurons
4.5
Intel has announced what for them is its first system capable of mimicking the human brain through neuromorphic computing . A total of 64 chips based on the company’s Loihi prototypes... Intel introduces a new neuromorphic system that mimics the human brain: equivalent to the calculation of 8 million neurons 4.5

Intel has announced what for them is its first system capable of mimicking the human brain through neuromorphic computing . A total of 64 chips based on the company’s Loihi prototypes that together amount to the calculation made by 8 million human neurons. In its initial phase, this new system will only be accessible to Intel partner researchers.

To put the figures in context, it is estimated that the human brain contains about 80 billion neurons. Ten thousand times more than this Intel chipset can calculate. But that does not detract from it, they say it can calculate 1,000 times faster and 10,000 times more efficiently than chips specialized in specific topics such as scattered coding or graph search.The system is codenamed ‘Pohoiki Beach’ and is based on the Loihi chip, which Intel already announced in September 2017 as a prototype. 64 Loihi chips working together to imitate the best possible functioning of a biological brain.

Processors with neuromorphic engineering

The attempt to imitate the human brain already gives some clues as to what the objective of this new Intel processor system is. Indeed, ‘Pohoiki Beach’ is designed for areas of artificial intelligence . It has been designed using the neuromorphic computing architecture, which seeks to mimic the biological neuronal system to obtain better calculations. In principle, it manages to adapt better to the changes and uses the knowledge it already has to learn exponentially over time.An Intel neuromorphic system with several Loihi chips.

Intel is not the only company that has meddled in this processor technology. Qualcomm has already produced neuromorphic chips . On the other hand, DeepMind, Alphabet’s machine learning company, uses deep learning methods that allow systems to learn on their own through the experience they acquire.

The strong point of Intel’s Loihi chip is energy consumption , as indicated. According to the first tests performed by some of Intel’s partners, this Loihi chip uses a hundred times less energy than a normal processor when performing machine learning calculations. When scaling the system they have only seen a 30% increase in energy consumption, compared to more than 500% that usually occurs using other systems.Thanks to this lower power consumption Intel has focused Loihi chips to the world of the Internet of Things (IoT). They believe that the new chips are ideal for devices that do not allow high power consumption but require advanced calculations for certain tasks.Intel Loihi chips in a Poomiki Beach neuromorphic system.

The 8 million neurons are just the beginning, Intel promises. They hope to release a new version of ‘Pohoiki Beach’ called ‘Pohoiki Spring’ by the end of this year. With this new version, they want to scale the system to achieve a calculation equivalent to 100 million neurons , still far from the 80 billion human brain, but a little closer.

Kim Hostler

I studied Communication Sciences because as a child I always wanted to be an announcer and make drawings for advertising campaigns. Life took me down another path and now I am a Communicator who has worked for Nokia, and Motorola. Where now instead of drawing, I take pictures, and instead of talking about my passion.