Energy efficient spiking neural network neuromorphic processing to enable decentralised service workflow composition in support of multi-domain operations

Bent, Graham; Simpkin, Christopher; Li, Yuhua; Preece, Alun

doi:10.1117/12.2617362

Cited by 1 publication

(2 citation statements)

References 19 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The approach we use is described in 3,4 and more recently in the context of multi-domain operations in two papers presented at SPIE'21 13 and SPIE'22. 14 Similarly service hypervectors can be bound and bundled to describe a workflow vector which is also a vector in the semantic vector space such that similar workflows have similar hypervectors. To configure different applications workflow hypervectors are injected into the network and through a process of unbinding and re-transmission, described in detail in the SPIE'21 paper, 13 the required services are discovered and connected in a completely decentralized manner.…”

Section: Motivating Examplementioning

confidence: 99%

“…10 Hypervectors also have recursive binding properties that allow for higher level semantic vector representations to be formulated from, and in the same format as their lower level semantic hypervector components. 12 Previous work reported at SPIE'21 13 and SPIE'22 14 has shown how symbolic hypervector descriptions of combat radios can be created by binding together component hypervectors that describe the radio characteristic and the platforms on which they are located. In this previous work the component or 'atomic' hypervectors comprised a set of random hypervectors that define the alphabet from which the words used to describe the services were constructed.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Semantic vector space mapping in edge of network multi-domain operations

Bent¹,

Summers-Stay

Preece

et al. 2023

Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications V

View full text Add to dashboard Cite

Artificial Intelligence applications are increasingly making use of vector embedding techniques to achieve impressive results in many application domains. Semantic Vector Spaces (SVS's) are constructed using semantic vector embedding techniques that learn vector representations of data across multiple domains. An important application area enabled by such techniques is the capability to represent software services and service workflows as semantic hypervectors. Previous work has shown how these hypervector representations have significant advantages over alternative schemes for decentralized service workflow construction, particularly in low communications bandwidth and energy constrained environments that are typical in multi-domain operations. SVS construction usually assumes that all the data required to construct the semantic vector space is available centrally. However, in multi-domain operations different partners may not be willing to share the training data necessary to construct a common multi-domain SVS. Hence semantic hypervectors representing similar services or workflows but constructed from different training data by different partners cannot be discovered and used. In this paper we focus on how it is possible to map semantic hypervectors between partner SVS's, so that complementary services and workflows developed and owned by different partners can be discovered and used to achieve mission goals. The paper describes techniques for generating the required mapping that require a minimum exchange of information between the different partners; demonstrate how it is possible to do this for semantic hypervectors that use different types of encoding (eg., real valued, binary, sparse slot-encoding); and illustrates how the mapping can be implemented in various multi-domain operational settings.

show abstract