Show simple item record

dc.contributor.authorKhan, Masood
dc.contributor.authorVice, Jordan
dc.date.accessioned2022-09-20T04:54:14Z
dc.date.available2022-09-20T04:54:14Z
dc.date.issued2022
dc.identifier.citationKhan, M. and Vice, J. 2022. Toward Accountable and Explainable Artificial Intelligence Part one: Theory and Examples. IEEE Access. 10: pp. 99686-99701.
dc.identifier.urihttp://hdl.handle.net/20.500.11937/89344
dc.identifier.doi10.1109/ACCESS.2022.3207812
dc.description.abstract

Like other Artificial Intelligence (AI) systems, Machine Learning (ML) applications cannot explain decisions, are marred with training-caused biases, and suffer from algorithmic limitations. Their eXplainable Artificial Intelligence (XAI) capabilities are typically measured in a two-dimensional space of explainability and accuracy ignoring the accountability aspects. During system evaluations, measures of comprehensibility, predictive accuracy and accountability remain inseparable. We propose an Accountable eXplainable Artificial Intelligence (AXAI) capability framework for facilitating separation and measurement of predictive accuracy, comprehensibility and accountability. The proposed framework, in its current form, allows assessing embedded levels of AXAI for delineating ML systems in a three-dimensional space. The AXAI framework quantifies comprehensibility in terms of the readiness of users to apply the acquired knowledge and assesses predictive accuracy in terms of the ratio of test and training data, training data size and the number of false-positive inferences. For establishing a chain of responsibility, accountability is measured in terms of the inspectability of input cues, data being processed and the output information. We demonstrate applying the framework for assessing the AXAI capabilities of three ML systems. The reported work provides bases for building AXAI capability frameworks for other genres of AI systems.

dc.publisherIEEE
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subject0801 - Artificial Intelligence and Image Processing
dc.subject4602 - Artificial intelligence
dc.titleToward Accountable and Explainable Artificial Intelligence Part one: Theory and Examples
dc.typeJournal Article
dcterms.source.issn2169-3536
dcterms.source.titleIEEE Access
dcterms.source.placeNew Jersey USA
dc.date.updated2022-09-20T04:54:07Z
curtin.departmentSchool of Civil and Mechanical Engineering
curtin.accessStatusOpen access
curtin.facultyFaculty of Science and Engineering
curtin.contributor.orcidKhan, Masood [0000-0002-2769-2380]
curtin.contributor.scopusauthoridKhan, Masood [7410317782]


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record

http://creativecommons.org/licenses/by/4.0/
Except where otherwise noted, this item's license is described as http://creativecommons.org/licenses/by/4.0/