The Reflexive Integrated Information Unit: A Differentiable Primitive for Artificial Consciousness

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: N'guessan, Gnankan Landry Regis, Karambal, Issa
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916796193308672
author N'guessan, Gnankan Landry Regis
Karambal, Issa
author_facet N'guessan, Gnankan Landry Regis
Karambal, Issa
contents Research on artificial consciousness lacks the equivalent of the perceptron: a small, trainable module that can be copied, benchmarked, and iteratively improved. We introduce the Reflexive Integrated Information Unit (RIIU), a recurrent cell that augments its hidden state $h$ with two additional vectors: (i) a meta-state $μ$ that records the cell's own causal footprint, and (ii) a broadcast buffer $B$ that exposes that footprint to the rest of the network. A sliding-window covariance and a differentiable Auto-$Φ$ surrogate let each RIIU maximize local information integration online. We prove that RIIUs (1) are end-to-end differentiable, (2) compose additively, and (3) perform $Φ$-monotone plasticity under gradient ascent. In an eight-way Grid-world, a four-layer RIIU agent restores $>90\%$ reward within 13 steps after actuator failure, twice as fast as a parameter-matched GRU, while maintaining a non-zero Auto-$Φ$ signal. By shrinking "consciousness-like" computation down to unit scale, RIIUs turn a philosophical debate into an empirical mathematical problem.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13825
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Reflexive Integrated Information Unit: A Differentiable Primitive for Artificial Consciousness
N'guessan, Gnankan Landry Regis
Karambal, Issa
Artificial Intelligence
Research on artificial consciousness lacks the equivalent of the perceptron: a small, trainable module that can be copied, benchmarked, and iteratively improved. We introduce the Reflexive Integrated Information Unit (RIIU), a recurrent cell that augments its hidden state $h$ with two additional vectors: (i) a meta-state $μ$ that records the cell's own causal footprint, and (ii) a broadcast buffer $B$ that exposes that footprint to the rest of the network. A sliding-window covariance and a differentiable Auto-$Φ$ surrogate let each RIIU maximize local information integration online. We prove that RIIUs (1) are end-to-end differentiable, (2) compose additively, and (3) perform $Φ$-monotone plasticity under gradient ascent. In an eight-way Grid-world, a four-layer RIIU agent restores $>90\%$ reward within 13 steps after actuator failure, twice as fast as a parameter-matched GRU, while maintaining a non-zero Auto-$Φ$ signal. By shrinking "consciousness-like" computation down to unit scale, RIIUs turn a philosophical debate into an empirical mathematical problem.
title The Reflexive Integrated Information Unit: A Differentiable Primitive for Artificial Consciousness
topic Artificial Intelligence
url https://arxiv.org/abs/2506.13825