Just like a fruit fly, a new algorithm never forgets old scents
Insect-inspired "sparse coding" does fast learning, avoids catastrophic forgetting.
Fruit flies may not be renowned for their intelligence, as demonstrated by their propensity to drown in wine glasses left out on patios. Despite their relatively simple brain of around 140,000 neurons—smaller than a poppy seed—these insects can rapidly process a vast array of scents and retain the memory of those smells for extended periods.
This remarkable ability surpasses that of modern electronic noses, which are typically costly, limited in their detection capabilities, and prone to forgetting previously learned odors once they encounter new ones. The question has arisen among researchers, including Kevin Max and Yang Shen from the Okinawa Institute of Science and Technology, who have developed an algorithm called Spi-Fly.
This algorithm is detailed in a recently published paper in the journal Neuromorphic Computing and Engineering.
Written by urgent.news from Ars Technica's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
Also reported by 1 other outlet
- Just like a fruit fly, a new algorithm never forgets old scents arstechnica.com
