Combinatorial Decision Dags: A Natural Computational Model for General Intelligence
This work proposes a foundational model for general intelligence, potentially impacting all of ML/AI, though it appears theoretical without empirical validation.
The paper introduces Combinatorial Decision Dags (CoDD), a novel computational model using combinatory logic to create higher-order decision trees, and shows it provides a natural framework for analyzing general intelligence through pattern recognition and formation, with extensions to quantum computing.
A novel computational model (CoDD) utilizing combinatory logic to create higher-order decision trees is presented. A theoretical analysis of general intelligence in terms of the formal theory of pattern recognition and pattern formation is outlined, and shown to take especially natural form in the case where patterns are expressed in CoDD language. Relationships between logical entropy and algorithmic information, and Shannon entropy and runtime complexity, are shown to be elucidated by this approach. Extension to the quantum computing case is also briefly discussed.