Science

New brain-inspired processor can hold a million artificial neurons

Obtaining artificial intelligence systems that process information in a similar way to humans is a real challenge, since the studies that aim to get closer to this objective are more and more numerous and refer to different axes. For their part, some manufacturers are trying to produce computer chips with artificial neurons whose architecture and function mimic those of the brain. They are called neuromorphic chips. Recently, Intel developed Loihi 2, a new version of its neuromorphic chip that contains one million artificial neurons.

This new version of the Loihi chip brings us a little closer to this dream, of one day obtaining intelligent electronic systems based on an improved version of the human brain. The analogy may seem like an exaggeration today, but it may not be in the relatively near future.

Until now, the neural networks that power major artificial intelligence systems function very differently from a brain. While the “neurons” used in deep learning pass numbers between them, biological neurons communicate through spikes of electrical activity whose significance is related to their timing and activation time.

Therefore, it is a very different language from that used by modern processors, and it has been difficult to effectively implement this type of neurons in conventional chips. To get around this hurdle, engineers specializing in neuromorphic systems are designing chips that mimic the architecture of biological neural networks, accommodating so-called “impulse” neural networks.

Faster and more energy efficient devices

In recent years, the field has attracted the interest of big tech companies like Intel, IBM, and Samsung. Today, pulse neural networks (SNNs) are considerably less developed than the deep learning algorithms that dominate modern AI research, but they have the potential to be much faster and better. Energy efficient, which makes them promising to integrate AI into devices with low power consumption. consumption, such as smartphones or robots.

It was in 2017 that Intel developed its first neuromorphic chip, called Loihi. This version can handle 125,000 neuron pulses. But this was only a modest first try for the company. Only 4 years later, the company presents a new version, Loihi 2, capable of implementing one million neurons. It is also ten times faster than its predecessor.

The Loihi 2 neuromorphic chip. © Intel

Loihi neurons carry information at the time of digitally represented pulses, which is more analogous to what happens in the brain. These pulses trigger neural computing, so it is not necessary to use a central clock to maintain synchronization. Also, a large part of the chip is idle when there are no events to watch, which saves power.

5,000 times faster than biological neurons

“Our second-generation chip dramatically improves the speed, programmability and capacity of neuromorphic processing, expanding its uses in smart computing applications under power and latency constraints,” said Mike Davies, director of Intel’s Neuromorphic Computing Laboratory.

Loihi 2 not only significantly increases the number of neurons, but also greatly expands their functionality. This is because the new chip is much more programmable, allowing it to implement a wide range of SNNs rather than the only type of model the previous chip could handle, explains IEEE Spectrum.

It can also support a wider variety of learning rules, which, among other things, should make it more compatible with the type of backpropagation learning approaches used in deep learning. Thanks to faster circuitry, the chip can now run 5,000 times faster than biological neurons, and improved interfaces on the chip make it easier for multiple neurons to run at the same time.

Each neuron can execute its own program

But the most important changes occur in the neurons themselves. Each neuron can run its own program, allowing a wide variety of different neurons to be implemented. Chip designers took the initiative to improve the way neurons work by allowing them to communicate using both timing and pulse power.

At this time, the company does not appear to have plans to commercialize the chips, which will only be available in the cloud to members of Intel’s neuromorphic research community. But Intel still seems motivated to further develop its neuromorphic ecosystem. Along with the new chip, it also released a new open source software framework called LAVA to help researchers create “neuro-inspired” applications that can run on any type of neuromorphic hardware or on conventional processors. “LAVA aims to contribute to the dissemination of [programmation] neuromorphic in the broader computing community, ”Davies told Ars Technica.

This announcement represents a crucial step for the company’s neuromorphic chips and could well be an important milestone towards the industrialization of these types of components. And even if Intel is not ready to turn it into a commercial activity, that does not mean that others are not … Brainchip, for example, based in Sydney, received its first neural processors in August and hopes to help customers develop systems. energy efficient.

PHP Script, Elementor Pro Weadown, WordPress Theme, Fs Poster Plugin Nulled, Newspaper – News & WooCommerce WordPress Theme, Wordfence Premium Nulled, Dokan Pro Nulled, Plugins, Elementor Pro Weadown, Astra Pro Nulled, Premium Addons for Elementor, Yoast Nulled, Flatsome Nulled, Woocommerce Custom Product Ad, Wpml Nulled,Woodmart Theme Nulled, PW WooCommerce Gift Cards Pro Nulled, Avada 7.4 Nulled, Newspaper 11.2, Jannah Nulled, Jnews 8.1.0 Nulled, WP Reset Pro, Woodmart Theme Nulled, Business Consulting Nulled, Rank Math Seo Pro Weadown, Slider Revolution Nulled, Consulting 6.1.4 Nulled, WeaPlay, Nulledfire

Back to top button