A Categorical Framework of General Intelligence
This foundational work addresses the problem of defining general intelligence mathematically, which is relevant to AI researchers and theorists.
The paper tackles the lack of mathematical foundations for general intelligence by introducing a categorical framework, with results including self-state awareness as a categorical analogue to self-consciousness and scenario representation using diagrams and limits for modeling and AI safety.
Can machines think? Since Alan Turing asked this question in 1950, nobody is able to give a direct answer, due to the lack of solid mathematical foundations for general intelligence. In this paper, we introduce a categorical framework towards this goal, with two main results. First, we investigate object representation through presheaves, introducing the notion of self-state awareness as a categorical analogue to self-consciousness, along with corresponding algorithms for its enforcement and evaluation. Secondly, we extend object representation to scenario representation using diagrams and limits, which then become building blocks for mathematical modeling, interpretability and AI safety. As an ancillary result, our framework introduces various categorical invariance properties that can serve as the alignment signals for model training.