Synthetic Ground Truth Generation for Evaluating Generative Policy Models

• DOI: 10.48550/arxiv.1904.13233
• Publication Date: 2019-01-01
• Authors: Daniel Cunnington; Graham White; Geeth de Mel
• Keywords: Representation; Viewpoints; Ground truth; Generative model; Battlespace

Generative Policy-based Models aim to enable a coalition of systems, be they devices or services adapt according contextual changes such as environmental factors, user preferences and different tasks whilst adhering various constraints regulations directed by managing party the collective vision coalition. Recent developments have proposed new architectures realize potential GPMs but complexity systems their associated requirements increases, there is an emerging requirement scenarios datasets realistically evaluate with respect properties operating environment, it future battlespace autonomous organization. In order address this requirement, in paper, we present method applying agile knowledge representation framework model requirements, both individualistic that enables synthetic generation ground truth data advanced can evaluated robustly complex environments. We also release conceptual models, annotated datasets, well means extend approach so similar developed for varying complexities situations.