Neuromorphic computing that mimics the human brain (opens in a new tab) is one step closer to reality, as researchers at Washington State University have built circuits crucial to this new type of computing using a pure substance little likely.
Using honey from bees, the researchers 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 the same way that synapses in the brain were between pairs of neurons.
After its creation, researchers at Washington State University tested the device's ability to rapidly turn on and off at speeds between 100 and 500 nanoseconds. The tests were successful, and the researchers hope their new memristor can help pave the way for sustainable, organic, biodegradable computing systems in the future.
In a press release (opens in a new tab) announcing the discovery, Feng Zhao, an associate professor in WSU's School of Engineering and Computer Science, provided additional information on honey's potential in creating chips of computer brains, saying:
"It's a very small device with a simple structure, but it has very similar functionality to a human neuron. This means that if we can integrate millions or billions of these honey memristors, they can be transformed into a highly functioning neuromorphic system." .like a human brain.
neuromorphic computing
Conventional computing systems, such as those found in commercial computers (opens in a new tab) and mobile workstations (opens in a new tab), are based on the von Neumann architecture, which includes inputs such as a keyboard and a mouse, as well as an output such as a monitor along with a CPU and RAM.
Link: The beginning of this link seems broken. The mechanisms from input to memory processing to output require much more power than the human brain. For example, Fujitsu's Fugaku supercomputer (opens in a new window) uses 28 million watts to run, while the human brain only uses 10 to 20 watts. That's why companies like Intel and IBM are working on neuromorphic chips (opens in a new tab) that mimic the workings of the human brain.
The human brain has more than 100 billion neurons with more than 1000 tons of synapses or connections between them. Since each neuron can process and store data, the brain is much more efficient than a traditional computer.
Meanwhile, conventional computer chips (opens in a new tab) are built from non-renewable and toxic materials, while neuromorphic chips, like the one created by researchers at Washington State University, can be made from biodegradable materials.
In the future, Zhao's team aims to shrink their honey memristors from a microscale that is about the size of a human hair to a nanoscale that is about 1/1000 of a human hair. By doing so, researchers will be able to bundle millions, if not billions, of honey memristors to create a complete neuromorphic computing system.