According to reports from researchers, microchips that have been built to mimic an insect’s nervous system have proved to be successful at helping solve technical issues such as object recognition and data mining.
Biomimetics is nothing new, with scientists copying various designs from nature and applying them in designs for things like cars or aircrafts. The same is true when it comes to copying the brain’s functions. Computing principles that underpin how the brain works, have become the inspiration behind programs known as neural networks, which are used to analyze data. Artificial neurons within these programmes mimic how a brain’s neurons operate. They can all receive, send and process information.
It is not possible to replicate these neurons exactly though. Real neurons need electrical impulses called spikes; it is these spikes that are difficult to copy when it comes to computing neural networks.
So to solve this issue, so-called “neuromorphic hardware” has been developed, providing models of spiking neurons on microchips.
“Biological neuronal networks that have been described by neuroscientists in the last few decades are a very rich source of inspiration for this task,” says neuroscientist and computer scientist Michael Schmuker.
Schmuker and his colleagues have turned to insects’ nervous systems for inspiration to design neuromorphic hardware with a “neural network”. In particular they studied the insect’s olfactory system, which it uses to smell. “The olfactory system deals with a very complex input space—chemical space,” Schmuker says. “This is reflected in its architecture, which supports parallel processing of a high number of different input channels. The insect olfactory system is particularly suited as inspiration because it is less complex than its vertebrate counterpart, while its basic blueprint is very similar.”
Potentially this “could be used as a building block for future neuromorphic supercomputers,” Schmuker says. “These computers will operate much like the brain, performing all computations in a massively parallel fashion.”
The scientists relied on the Spikey neuromorphic microchip developed at the University of Heidelberg in Germany. The device can perform 10,000 times faster than its biological counterparts.
It is important to note that the scientists do not feel that neuromorphic computers will replace conventional computers.
“Rather, we are developing a new brain-inspired technique for computing that will be able to solve problems for which conventional computers are not well-suited,” Schmuker says.
You can find Schmuker and his colleagues’ findings in the Proceedings of the National Academy of Sciences journal.
[Image via Pinterest]