Chrisley, Ron (2018) Grounded metacognitive architectures for machine consciousness. AAAI Spring Symposium on “Towards Conscious AI Systems", Stanford, CA, March 25-27, 2019. Published in: Towards Conscious AI Systems: Papers of the 2019 Symposium (Association for the Advancement of Artificial Intelligence 2019 Spring Symposium Series), Stanford, CA, March 25-27, 2019. 1-7. RWTH Aachen University ISSN 1613-0073

PDF - Published Version Download (376kB)

Abstract

Multiple approaches to machine consciousness emphasise the importance of metacognitive states and processes. A considerable num- ber of cognitive systems researchers prefer architectures that are not classically symbolic, and in which learning, rather a priori structure, is central. But it is unclear how these grounded architectures can support metacognition of the required sort. To investigate this possibility, a basic design sketch of such an architecture is presented.

Item Type:	Conference Proceedings
Keywords:	Metacognition, Sub-symbolic Computation, Cognitive Architecture, Symbol Grounding, Neural Networks, Machine Consciousness
Schools and Departments:	School of Engineering and Informatics > Informatics
Research Centres and Groups:	Centre for Cognitive Science Sackler Centre for Consciousness Science
Depositing User:	Ron Chrisley
Date Deposited:	12 Mar 2020 08:50
Last Modified:	12 Mar 2020 08:51
URI:	http://sro.sussex.ac.uk/id/eprint/90354

View download statistics for this item

📧 Request an update