This is a past event
To realise accountable AI systems, different types of information from a range of sources need to be recorded throughout the system life cycle. In the RAInS project, we argue that knowledge graphs can support capture and audit of such information; however, the creation of such accountability records must be planned for and performed within different life cycle stages. This seminar covers our provenance-based approach to support not only the capture of accountability information, but also abstract descriptions of accountability plans that guide its collection processes, all as part of a single knowledge graph. The seminar introduces the (1) SAO ontology, a lightweight generic ontology for describing accountability plans and their corresponding accountability traces of computational systems; (2) the RAInS ontology, which extends SAO to model accountability information relevant to the design and implementation stages of AI systems; and (3) the Accountability Fabric, a proof-of-concept implementation of a suite of semantic tools utilising SAO and RAInS to provide a visual interface for designing accountability plans, and managing and auditing accountability records.
- Speaker
- Iman Naja
- Venue
- Meston 2 and Teams