The neural cognitive architecture

Huyck, Christian R. (2017) The neural cognitive architecture. In: AAAI 2017 FALL Symposium Series: Symposium on A Standard Models of the Mind, 09-11 Nov 2017, Arlington, Virginia, USA.

[img]
Preview
PDF - Final accepted version (with author's formatting)
Download (68kB) | Preview

Abstract

The development of a cognitive architecture based on neurons is currently viable. An initial architecture is proposed, and is based around a slow serial system, and a fast parallel system, with additional subsystems for behaviours such as sensing, action and language. Current technology allows us to emulate millions of neurons in real time supporting the development and use of relatively sophisticated systems based on the architecture. While knowledge of biological neural processing and learning rules, and cognitive behaviour is extensive, it is far from complete. This architecture provides a slowly varying neural structure that forms the framework for cognition and learning. It will provide support for exploring biological neural behaviour in functioning animals, and support for the development of artificial systems based on neurons.

Item Type: Conference or Workshop Item (Paper)
Research Areas: A. > School of Science and Technology > Computer Science > Artificial Intelligence group
Item ID: 22926
Notes on copyright: This is the author's accepted manuscript included in this repository with permission of the publisher AAAI. The final published paper appears as: HUYCK, C.. The Neural Cognitive Architecture. AAAI Fall Symposium Series, North America, oct. 2017. Published by the Association for the Advancement of Artificial Intelligence (AAAI), available at available at: https://aaai.org/ocs/index.php/FSS/FSS17/paper/view/15954
Useful Links:
Depositing User: Chris Huyck
Date Deposited: 13 Nov 2017 13:17
Last Modified: 03 Apr 2019 18:16
URI: https://eprints.mdx.ac.uk/id/eprint/22926

Actions (login required)

Edit Item Edit Item

Full text downloads (NB count will be zero if no full text documents are attached to the record)

Downloads per month over the past year