AI RESEARCH
From Entropy to Epiplexity: Rethinking Information for Computationally Bounded Intelligence
arXiv CS.LG
•
ArXi:2601.03220v2 Announce Type: replace Can we learn from data than existed in the generating process itself? Can new and useful information be constructed from merely applying deterministic transformations to existing data? Can the learnable content in data be evaluated without considering a downstream task? On these questions, Shannon information and Kolmogoro complexity come up nearly empty-handed, in part because they assume observers with unlimited computational capacity and do not target the useful information content.