Just like a fruit fly, a new algorithm never forgets old scents

Spi-Fly, an algorithm developed by Kevin Max and Yang Shen at the Okinawa Institute of Science and Technology, mimics the olfactory processing of fruit flies. It uses a network of roughly 140,000 artificial neurons to detect a wide range of odors quickly and retain each scent’s memory over time. The design aims to overcome limitations of current electronic noses, which are costly, narrowly focused, and forget odors when new ones are learned.