Rats perceive the world with a complexity that modern artificial neural networks struggle to match. This is the finding of a recent study published in the journal Patterns by the Visual Neuroscience Lab of the Scuola Internazionale Superiore di Studi Avanzati (SISSA), led by Davide Zoccolan. Using a convolutional neural network (CNN), a type of artificial intelligence particularly effective at recognizing image content, researchers attempted to replicate rats' ability to recognize objects under various conditions, altering the objects' sizes, positions, rotations, and partially obscuring them.
The results reveal that, even compared to advances in artificial intelligence, rat vision is extremely efficient and adaptable. As the complexity of image manipulations increases, the neural network requires more resources to compete with rat discrimination ability. Additionally, rats and artificial intelligence employ different image processing strategies, suggesting that neural networks have still something to learn from neuroscience.
Read the full press release: