Neuromorphic computing that mimics the human brain (opens in new tab) is one step closer to reality as researchers from Washington State University have built a crucial circuit for this new type of computing using an unlikely pure substance.
Using bee-sourced honey, the researchers have built a proof-of-concept memory resistor or memristor. To accomplish this feat, they first turned the honey into a solid form and then held it between two metal electrodes in a similar way to how the brain’s synapses lay between pairs of neurons.
Following its creation, Washington State University researchers tested the device’s ability to quickly switch on and off at speeds ranging between 100 and 500 nanoseconds. The tests were successful and the researchers hope that their new memristor can help pave the way for biodegradable, sustainable and organic-based computing systems going forward.
In a press release (opens in new tab) announcing the discovery, associate professor of WSU’s School of Engineering and Computer Science, Feng Zhao provided further insight on honey’s potential in the creation of brain-like computer chips, saying:
“This is a very small device with a simple structure, but it has very similar functionalities to a human neuron. This means if we can integrate millions or billions of these honey memristors together, then they can be made into a neuromorphic system that functions much like a human brain.”
Conventional computer systems like those found in business computers (opens in new tab) and mobile workstations (opens in new tab) are based on the von Neumann architecture which involves an input such as a keyboard and mouse as well as an output like a monitor along with a CPU and RAM.
Link: The start of this link looks broken.echanisms from input to processing to memory to output takes a lot more power when compared to the human brain. For instance Fujitsu’s Fugaku (opens in new tab) supercomputer uses 28 million watts in order to run while the human brain uses only around 10 to 20 watts. This is why companies like Intel and IBM are working on neuromorphic chips (opens in new tab) that mimic how the human brain functions.
The human brain has over 100bn neurons with more than 1,000tn synapses or connections among them. As 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 built using nonrenewable and toxic materials while neuromorphic chips, like the one created by researchers at Washington State University, can be made using biodegradable materials instead.
Going forward, Zhao’s team aims to shrink the size of its honey memristors from a microscale that is about the size of a human hair to a nanoscale which is about 1/1000 of a human hair. By doing so, the researchers will be able to bundle millions or even billions of honey memristors together to make a full neuromorphic computing system.