Just like a fruit fly, a new algorithm never forgets old scents
Insect-inspired "sparse coding" does fast learning, avoids catastrophic forgetting.
Fruit flies, while not known for their intellect, possess brains that are smaller than a poppy seed yet capable of processing a wide range of scents in mere fractions of a second. Remarkably, they can also retain these memories for extended periods. In comparison to modern electronic noses, Drosophila demonstrate superior performance.
However, even the most sophisticated electronic noses on the market are often prohibitively expensive, limited in their detection capabilities, and prone to quickly forgetting scents once they learn new ones. This prompted researchers to ponder whether the fly's abilities could be replicated. This is the very question that Kevin Max and Yang Shen from the Okinawa Institute of Science and Technology have been grappling with.
Through their recent work, they have developed an algorithm called Spi-Fly, which has recently been detailed in a paper published in the journal Neuromorphic Computing and Engineering.
Written by urgent.news from Ars Technica Science's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
- Just like a fruit fly, a new algorithm never forgets old scents arstechnica.com
