Researchers at the Massachusetts Institute of Technology (MIT)looked at how artificial neural networks (used in artificial intelligence (AI) systems) process information, and found that individual neurons in such networks could be highly correlated to high-level concepts involved in decision-making (such as identifying patterns and concepts in an image). In scientific terms, tracing the recognition of specific concepts to a specific neuron can be used to objectively measure bias imparted in a neural network by its training data. In more practical terms, identifying the specific neuron in an artificial neural network that is responsible for a certain decision could pave the way to determining why an AI system makes one decision over another (w.g. why a driverless car makes certain decisions while on the road).