A groundbreaking study conducted by engineers at the University of Massachusetts Amherst has developed an artificial neuron whose electrical activity closely matches that of natural brain cells.
The innovations primarily build on the team’s earlier research using conductive filaments made from electricity producing bacteria.
This new innovation accelerates the new ways for computers that run with efficiency of living systems and may even connect directly with biological issues.
The human body, specifically the brain, exhibits superior electrical performance-more than 100 times greater than the typical computer circuit.
Performing a task such as writing a story uses only about 20 watts of power in the human brain, whereas a large language model requires more than a megawatt to accomplish the same task.
However, engineers have long desired to design artificial intelligence neurons for more energy-efficient computing, but turning down their voltage to match biological levels has been a major impediment.
Jun Yao, an associate professor of electrical and computer engineering at UMass Amherst, said, "Previous versions of official neurons used 10 times more voltage- and 100 times more power than the one we have created."
The earlier designs were insufficient and couldn't connect directly with living neurons which are sensitive to stronger electrical signals.
Yao said, "Ours registers only 0.1 volts which is about the same as the neurons in our bodies."
The new neuron by Fu and Yao has broad applicability from designing computers along bio-inspired and effective principles to creating electronic devices that can communicate directly with our bodies.
Yao stated, "We currently have all kinds of wearable electronic sensing systems, but they are comparatively clunky and inefficient."
Researchers explained that every time they sensed a signal from our body, they had to electrically intensify it so that a computer could analyze it.
That intermediate step of amplification increases both power consumption and the circuit’s complexity, but sensors built with our low-voltage neurons could do without any amplification at all.
The secret ingredient in the team’s artificial neuron is a protein nanowire, synthesized from the remarkable bacteria Geobacter sulfurreducens which also has the ability to generate electricity.
The research team have used the bacteria’s protein nanowires to design a whole host of exceedingly efficient devices.
The advancement in artificial neurons is significant because the ultra-low voltage devices incorporating protein nanowires from bacteria, work like the real ones.
Future implications may include sensors powered by devices that harvest electricity from thin year.