Consciousness as a Functor
Sridhar Mahadevan
arXiv Preprint Archive August 25, 2025 preprint
Study at a glance
AI-extracted from the abstract| Characteristics | Theoretical or philosophical paper |
|---|---|
| Keywords | Cs.ai Cs.lg |
| Key points | Proposes that consciousness can be modeled as a functor transmitting content between unconscious and conscious memory, using category theory and reinforcement learning frameworks. |
Abstract
We propose a novel theory of consciousness as a functor (CF) that receives and transmits contents from unconscious memory into conscious memory. Our CF framework can be seen as a categorial formulation of the Global Workspace Theory proposed by Baars. CF models the ensemble of unconscious processes as a topos category of coalgebras. The internal language of thought in CF is defined as a Multi-modal Universal Mitchell-Benabou Language Embedding (MUMBLE). We model the transmission of information from conscious short-term working memory to long-term unconscious memory using our recently proposed Universal Reinforcement Learning (URL) framework. To model the transmission of information from unconscious long-term memory into resource-constrained short-term memory, we propose a network economic model.