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

Researchers developed an algorithm based on how fruit flies process odors that learns new information quickly while retaining previously learned associations. The approach, called sparse coding, mimics the fruit fly olfactory system and addresses a challenge in artificial intelligence where neural networks forget old information when learning new tasks. The algorithm was tested on tasks involving odor recognition and demonstrated faster learning speeds compared to standard methods while maintaining memory of earlier training.

Next story