Humans can detect over one trillion smells. It will be a scientific breakthrough if machine learning manages to sense even one percent of that. But researches have taken the first step and demonstrated the ability of Intel’s Loihi chip, a neuromorphic chip, to learn and recognize the scent of at least 10 different hazardous chemicals.
In a joint study, researchers claimed the chip could identify specific smells, despite “significant” data noise in the surroundings. This chip bundles over 2 billion transistors and 130,000 artificial neurons. In this case, Intel’s Loihi chip tried to mimic the brain’s olfactory system, which is responsible for the sense of smell.
This work is an example of contemporary research at the crossroads of neuroscience and artificial intelligence and demonstrates Loihi’s potential to provide important sensing capabilities that could benefit various industries, such as detecting weapons and explosives, finding narcotics and diagnosing diseases.