A demonstration of vector symbolic architecture as an effective integrated technology for AI at the network edge

Bent, Graham A., Davies, Cai, Roig Vilamala, Marc, Li, Yuhua ORCID: https://orcid.org/0000-0003-2913-4478, Preece, Alun D. ORCID: https://orcid.org/0000-0003-0349-9057, Di Caterina, Gaetano, Vicente Sola, Alex, Kirkland, Paul, Pearson, Gavin, Tutcher, Benomy, Bouma, Henri, Yitzhaky, Yitzhak, Prabhu, Radhakrishna and Kuijf, Hugo J. 2024. A demonstration of vector symbolic architecture as an effective integrated technology for AI at the network edge. Presented at: Artificial Intelligence for Security and Defence Applications II, Edinburgh, UK, 17–19 September 2024. Published in: Bouma, H., Prabhu, R., Yitzhaky, Y. and Kuijf, H. J. eds. Proceedings of Artificial Intelligence for Security and Defence Applications II. (132061) SPIE, pp. 39-55. 10.1117/12.3030952

Preview

PDF - Accepted Post-Print Version Download (7MB) | Preview

Abstract

Vector Symbolic Architecture (VSA), a.k.a. Hyperdimensional Computing has transformative potential for advancing cognitive processing capabilities at the network edge. This paper presents a technology integration experiment, demonstrating how the VSA paradigm offers robust solutions for generation-after-next AI deployment at the network edge. Specifically, we show how VSA effectively models and integrates the cognitive processes required to perform intelligence, surveillance, and reconnaissance (ISR). The experiment integrates functions across the observe, orientate, decide and act (OODA) loop, including the processing of sensed data via both a neuromorphic event-based camera and a standard CMOS frame-rate camera; declarative knowledge-based reasoning in a semantic vector space; action planning using VSA cognitive maps; access to procedural knowledge via large language models (LLMs); and efficient communication between agents via highly-compact binary vector representations. In contrast to previous ‘point solutions’ showing the effectiveness of VSA for individual OODA tasks, this work takes a ‘whole system’ approach, demonstrating the power of VSA as a uniform integration technology.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Schools:	Schools > Computer Science & Informatics Research Institutes & Centres > Crime and Security Research Institute (CSURI)
Publisher:	SPIE
Funders:	Dstl
Date of First Compliant Deposit:	4 February 2025
Date of Acceptance:	1 July 2024
Last Modified:	10 Mar 2025 10:00
URI:	https://orca.cardiff.ac.uk/id/eprint/175872

Actions (repository staff only)

Edit Item