Projection: a mechanism for human-like reasoning in Artificial Intelligence

Artificial Intelligence systems cannot yet match human abilities to apply knowledge situations that vary from what they have been programmed for, or trained for. In visual object recognition, methods of inference exploiting top-down information (from a model) shown be effective for recognising entities in difficult conditions. Here component this type inference, called ‘projection’, is key mechanism solve the problem applying varied challenging situations, across range AI domains, such as vision, robotics, language. Finally, relevance projection tackling commonsense discussed.