A comparison of simple agents implemented in simulated neurons

Huyck, Christian R. ORCID logoORCID: https://orcid.org/0000-0003-4015-3549, Evans, Carl ORCID logoORCID: https://orcid.org/0000-0002-3109-595X and Mitchell, Ian ORCID logoORCID: https://orcid.org/0000-0002-3882-9127 (2015) A comparison of simple agents implemented in simulated neurons. Biologically Inspired Cognitive Architectures, 12 . pp. 9-19. ISSN 2212-683X [Article] (doi:10.1016/j.bica.2015.03.001)

This is the latest version of this item.

PDF - First submitted uncorrected version (with author's formatting)
Available under License Creative Commons Attribution-NonCommercial-NoDerivatives 4.0.

Download (76kB) | Preview


Neuromorphic embodied cell assembly agents that learn are one application being developed for the Human Brain Project (HBP). The HBP is building tools, available for all researchers, for building brain simulations. Existing simulated neural Cell Assembly agents are being translated to the platforms provided by the HBP; these agents run on neuromorphic chips in addition to von Neumann based computers. Whilst translation of the agents to the software technology demanded by the HBP platforms is relatively straightforward, porting to the neuromorphic chips is a non-trivial software engineering task. Versions of the simple agent, CABot1, have been developed in fatiguing leaky integrate and fire neurons, Izhikevich neurons and leaky integrate and fire neurons. These have been developed to run in Java, PyNN, NEST and Neuromorphic hardware. All variants are roughly equivalent. The agents view a picture, implement simple commands, and respond to a context sensitive directive involving the content of the picture. By running variants of these agents on different platforms, and with the different simulated neural models, implicit assumptions in these models can be revealed. Once these Cell Assembly agents have been translated and embodied in a virtual environment, they will be extended to learn more effectively. The use of neural hardware supports the real time simulation of many more neurons, providing a platform for exploration of more complex simulated neural systems.

Item Type: Article
Additional Information: Accepted 23 March 2015, Available online 21 April 2015.
Research Areas: A. > School of Science and Technology > Computer Science > Artificial Intelligence group
Item ID: 15308
Useful Links:
Depositing User: Chris Huyck
Date Deposited: 27 Apr 2015 08:41
Last Modified: 29 Nov 2022 22:54
URI: https://eprints.mdx.ac.uk/id/eprint/15308

Available Versions of this Item

  • A comparison of simple agents implemented in simulated neurons. (deposited 27 Apr 2015 08:41) [Currently Displayed]

Actions (login required)

View Item View Item


Activity Overview
6 month trend
6 month trend

Additional statistics are available via IRStats2.