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

Bent, Graham and Davies, Cai and Roig Vilamala, Marc and Li, Yuhua and Preece, Alun and Di Caterina, Gaetano and Vicente Sola, Alex and Kirkland, Paul and Pearson, Gavin and Tutcher, Benomy; (2024) A demonstration of vector symbolic architecture as an effective integrated technology for AI at the network edge. In: SPIE Sensors + Imaging. SPIE, GBR. (In Press)

[thumbnail of Bent-etal-SPIE-2024-A-demonstration-of-vector-symbolic-architecture-as-an-effective-integrated-technology-for-AI] Text. Filename: Bent-etal-SPIE-2024-A-demonstration-of-vector-symbolic-architecture-as-an-effective-integrated-technology-for-AI.pdf
Accepted Author Manuscript
Restricted to Repository staff only until 1 January 2099.
Download (29MB) | Request a copy

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.

ORCID iDs

Bent, Graham, Davies, Cai, Roig Vilamala, Marc, Li, Yuhua, Preece, Alun, Di Caterina, Gaetano ORCID logoORCID: https://orcid.org/0000-0002-7256-0897, Vicente Sola, Alex ORCID logoORCID: https://orcid.org/0000-0002-2370-6562, Kirkland, Paul ORCID logoORCID: https://orcid.org/0000-0001-5905-6816, Pearson, Gavin and Tutcher, Benomy;
CORE (COnnecting REpositories)