Projection: A Mechanism for Human-like Reasoning in Artificial Intelligence
This addresses the commonsense knowledge problem in AI, which is a foundational challenge for developing more adaptable and general systems.
The paper tackles the problem of AI systems' inability to apply knowledge to varied or challenging situations, proposing that 'projection'—a mechanism inspired by top-down inference in visual object recognition—is key to enabling human-like reasoning across domains like vision, robotics, and language.
Artificial Intelligence systems cannot yet match human abilities to apply knowledge to 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) have been shown to be effective for recognising entities in difficult conditions. Here this type of inference, called `projection', is shown to be a key mechanism to solve the problem of applying knowledge to varied or challenging situations, across a range of AI domains, such as vision, robotics, or language. Finally the relevance of projection to tackling the commonsense knowledge problem is discussed.