(ORDO NEWS) — Honey could be the sweet spot for developing environmentally friendly components for neuromorphic computers, systems designed to mimic the neurons and synapses found in the human brain.
Neuromorphic systems, which some have called the future of computing, run much faster and consume far less power than traditional computers.
Engineers have demonstrated one way to make them more organic by using honey to make a memristor, a transistor-like component that can not only process but also store data in memory.
VANCOUVER, Washington. – Honey could be a sweet solution for the development of environmentally friendly components for neuromorphic computers – systems designed to mimic the neurons and synapses found in the human brain.
Neuromorphic systems, which some have called the future of computing, run much faster and consume far less power than traditional computers.
Washington State University engineers showed one way to make them more organic. In a study published in the Journal of Physics D, scientists show that honey can be used to create a memristor, a transistor-like component that can not only process but also store data in memory.
“This is a very small device with a simple structure, but its functionality is very similar to that of a human neuron,” said Feng Zhao, an assistant professor in the VSU School of Engineering and Computer Science and the study’s corresponding author.
“This means that if we can combine millions or billions of these honey memristors together, then they can be turned into a neuromorphic system that functions like a human brain.”
For Zhao’s research, and first author Brandon Sueoka, a VSU graduate student in Zhao’s lab, created memristors by processing honey into a solid form and placing it between two metal electrodes, creating a structure similar to a human synapse.
They then tested the ability of honey memristors to mimic synapses at high turn-on and turn-off speeds of 100 and 500 nanoseconds, respectively.
The memristors also mimicked synapse functions known as spike time-dependent plasticity and spike velocity-dependent plasticity, which are responsible for learning processes in the human brain and the storage of new information in neurons.
VSU engineers have created honey memristors on the microscale, so they are the size of a human hair. A research team led by Zhao plans to develop them at the nanoscale, roughly 1/1000th of a human hair, and join many millions or even billions together to create a complete neuromorphic computing system.
Currently, conventional computer systems are based on the so-called von Neumann architecture. Named after its creator, this architecture includes an input, usually a keyboard and mouse, and an output, such as a monitor.
It also has a central processing unit, or central processing unit, and random access memory, or memory for storing data.
Passing data through all these mechanisms, from input to processing, from memory to output, requires a lot of energy, at least compared to the human brain, Zhao said. For example, the Fugaku supercomputer requires up to 28 megawatts, which is approximately equal to 28 million watts, while the brain consumes only 10-20 watts.
The human brain has over 100 billion neurons with over 1,000 trillion synapses, or connections, between them. Each neuron can both process and store data, making the brain far more efficient than a traditional computer, and neuromorphic computing systems developers are aiming to mimic this structure.
Several companies, including Intel and IBM, have released neuromorphic chips that have the equivalent of over 100 million “neurons” per chip, but that’s still nowhere close to the number of neurons in a brain. In addition, many developers are still using the same non-renewable and toxic materials that are used in conventional computer chips today.
Many researchers, including Zhao’s team, are looking for biodegradable and renewable solutions for this promising new type of computing. Zhao is also leading research into using proteins and other sugars, such as those found in aloe vera leaves, but he sees great potential in honey.
“Honey doesn’t spoil,” he said. It has a very low moisture concentration, so bacteria cannot survive in it. “This means that these computer chips will be very stable and reliable for a very long time.”
The honey memristor chips developed at VSU must be able to withstand the lower levels of heat generated by neuromorphic systems, which don’t get as hot as traditional computers. Honey memristors will also reduce e-waste.
“When we want to dispose of devices that use honey computer chips, we can easily dissolve them in water,” he said. “Thanks to these special properties, honey is very useful for creating renewable and biodegradable neuromorphic systems.”
It also means, Zhao warns, that, as with conventional computers, users will have to avoid spilling coffee on them.
—
Online:
Contact us: [email protected]
Our Standards, Terms of Use: Standard Terms And Conditions.