Neuromorphic computing that mimics the human brain (opens in new tab) is one step closer to reality as researchers at Washington State University have built a crucial circuit for this new kind of computing using an impossibly pure substance.
Using bee honey, researchers built a proof-of-concept memory resistor, or memristor. To accomplish this feat, they first formed the honey into a solid form and then held it between two metal electrodes, much like the brain’s synapses are between pairs of neurons.
After its development, researchers at Washington State University tested the device’s ability to turn itself on and off rapidly at speeds between 100 and 500 nanoseconds. The tests were successful and the researchers hope their new memristor can help pave the way for biodegradable, sustainable and organic computing systems for the future.
In a press release (opens in new tab) Feng Zhao, associate professor at the WSU School of Engineering and Computer Science, announced the discovery and provided further insight into honey’s potential in making brain-like computer chips:
“This is a very small device with a simple structure, but it has very similar functions to a human neuron. That means if we can integrate millions or billions of these honey memristors together, they can be made into a neuromorphic system that works much like a human brain.”
Neuromorphic Computing
Traditional computing systems found in business computers (opens in new tab) and mobile workstations (opens in new tab) are based on the von Neumann architecture, which includes an input such as a keyboard and mouse and an output such as a monitor along with a CPU and RAM.
Shortcut: The beginning of this shortcut looks broken. Mechanisms from input to processing to storage to output require much more power compared to the human brain. For example, Fujitsu’s Fugaku (opens in new tab) A supercomputer uses 28 million watts to run, while the human brain uses only about 10 to 20 watts. That’s why companies like Intel and IBM are working on neuromorphic chips (opens in new tab) that mimic how the human brain works.
The human brain has over 100 billion neurons with more than 1,000 trillion synapses, or connections between them. Because each neuron can both process and store data, the brain is much more efficient than a traditional computer.
At the same time conventional computer chips (opens in new tab) are made from non-renewable and toxic materials, while neuromorphic chips, such as those developed by Washington State University researchers, can be made from biodegradable materials instead.
In the future, Zhao’s team aims to shrink the size of its honey memristors from a micro scale, roughly the size of a human hair, to a nano scale, roughly 1/1000 the size of a human hair. In this way, researchers will be able to combine millions or even billions of honey memristors into a complete neuromorphic computing system.
