Artificial intelligence is increasingly used in everyday life, from medical diagnosis to autonomous vehicles, but many of these systems remain difficult to understand. They can make accurate predictions, yet their internal decision-making processes are often opaque. 

The EU-funded Neurosci-ANNs project addresses this challenge by studying how artificial neural networks (ANNs) work internally. Instead of focusing on individual components, it examines how groups of artificial neurons represent and process information to produce decisions. 

Inspired by neuroscience, the project applies tools originally developed to study the brain to better understand AI systems. The goal is to make these systems more transparent, reliable, and efficient, especially in applications where trust and interpretability are essential.