Consciousness and Automated Reasoning
Ulrike Barthelmeß, Ulrich Furbach, Claudia Schon
arXiv Preprint Archive January 26, 2020 via arXiv
Summary
AI-generated from the abstractA first-order logic reasoning system paired with a large knowledge base can function as an artificial consciousness system. Drawing on Tononi's Information Integration Theory and Baars' Global Workspace Theory, the paper applies these frameworks to the Hyper reasoning system using ConceptNet for commonsense and cognitive reasoning. The system demonstrates the ability to perform conscious mind wandering, suggesting that such architectures can exhibit key features of consciousness.
Study at a glance
| Characteristics | Theoretical or philosophical paper Peer reviewed |
|---|---|
| Keywords | Cs.ai |
| Key finding | Proposes that a first-order logic reasoning system paired with a large knowledge base can be understood as an artificial consciousness system capable of conscious mind wandering. |
Abstract
This paper aims at demonstrating how a first-order logic reasoning system in combination with a large knowledge base can be understood as an artificial consciousness system. For this we review some aspects from the area of philosophy of mind and in particular Tononi's Information Integration Theory (IIT) and Baars' Global Workspace Theory. These will be applied to the reasoning system Hyper with ConceptNet as a knowledge base within a scenario of commonsense and cognitive reasoning. Finally we demonstrate that such a system is very well able to do conscious mind wandering.