Honey Could Be Used for Making Neuromorphic, Brain-Like CPUs

Many of the key features that made artificial intelligence so powerful have historically been powered by GPUs, which are limited in their ability to scale. A group at UC Berkeley has developed a new chip design called Hexiwear with integrated neuromorphic hardware and biological computing capabilities. This is designed specifically for AI-powered smart devices like VR headsets, AR glasses and more.,

Honey Could Be Used for Making Neuromorphic, Brain-Like CPUs. Honey is a viscous liquid that can be used to make neuromorphic chips. This article discusses the use of honey in creating brain-like computers.

Image courtesy of StudioCanal

If you’re ever shot down by a Terminator with a neural net processah (a learning computah), sweet honey might be somewhat to blame. Researchers at Washington State University found that the delicious chemical has the potential to be used to create neuromorphic chips, which are processors that are meant to function and process information in the same way as the human brain does, with neurons and synapses mimicked. Engineers discovered that honey in solid form may be utilized to create effective memristors, which, unlike transistors, can not only process but also store data in memory. A neuromorphic computing system’s efficiency and processing speed are only two of its advantages.

“This is a very little device with a very basic construction, yet it has very comparable functions to a human neuron,” said Feng Zhao, an associate professor at WSU’s School of Engineering and Computer Science and the study’s corresponding author. “This implies that if we can combine millions or billions of these honey memristors, we can create a neuromorphic system that works similarly to a human brain.”

Honey has the potential to be used to create computer chips that look like brains (WSU)

Neuromorphic systems, dubbed the “future of computing” by some, are more quicker and use much less power than standard computers. Engineers at Washington State University have proven one approach to make them more organic. Honey may be used to construct a memristor, a component comparable to a transistor that can not only process but also store data in memory, according to a study published in Journal of Physics D.

Zhao and lead author Brandon Sueoka, a WSU graduate student in Zhao’s lab, made memristors by solidifying honey and sandwiching it between two metal electrodes, creating a structure that resembles a human synapse. The honey memristors were then put to the test, with high switching on and off rates of 100 and 500 nanoseconds, to see whether they could imitate the function of synapses. The memristors also mimicked the synaptic functions known as spike-timing dependent plasticity and spike-rate dependent plasticity, which are crucial for learning and maintaining new information in neurons in humans.

The honey memristors were built on a micro-scale by WSU engineers and are roughly the size of a human hair. Zhao’s team hopes to construct them on a nanoscale, roughly 1/1000 of the width of a human hair, and then bundle millions or perhaps billions of them together to create a comprehensive neuromorphic computing system.

Return to the thread

Recent Developments

Ubisoft has stopped developing Ghost Recon Breakpoint.

5 April 2022 5 April 2022

The GPU of the NVIDIA GeForce RTX 4090 is estimated to use 450 Watts on its own.

5 April 2022 5 April 2022

Life Is Strange: True Colors, Chinatown Detective Agency, and Other Xbox Game Pass Titles for April

5 April 2022 5 April 2022

The NH-D12L is a low-height dual-tower CPU cooler with a new NF-A12x25r PWM fan from Noctua.

5 April 2022 5 April 2022

Noctua Confirms AMD’s Next-Generation AM5 Socket and Ryzen 7000 Series Processors Cooler Support

5 April 2022 5 April 2022

Unreal Engine 5 is now available for download from Epic Games.

5 April 2022 5 April 2022

The “neuromorphic accelerators” are a way to make computers more like the human brain. They can be used to create intelligent machines that can learn and adapt, which could lead to more advanced robots.

Related Tags

• memory chip for human brain
• google neuromorphic computing
• neuromorphic hardware companies
• neuromorphic computing projects
• neuromorphic computing course