Zobrazeno 1 - 10
of 216
pro vyhledávání: '"Habli, Ibrahim"'
Autor:
Vardal, Ozan, Hawkins, Richard, Paterson, Colin, Picardi, Chiara, Omeiza, Daniel, Kunze, Lars, Habli, Ibrahim
For machine learning components used as part of autonomous systems (AS) in carrying out critical tasks it is crucial that assurance of the models can be maintained in the face of post-deployment changes (such as changes in the operating environment o
Externí odkaz:
http://arxiv.org/abs/2406.16220
Autor:
Kaas, Marten H. L., Burr, Christopher, Porter, Zoe, Ozturk, Berk, Ryan, Philippa, Katell, Michael, Polo, Nuala, Westerling, Kalle, Habli, Ibrahim
Fairness is one of the most commonly identified ethical principles in existing AI guidelines, and the development of fair AI-enabled systems is required by new and emerging AI regulation. But most approaches to addressing the fairness of AI-enabled s
Externí odkaz:
http://arxiv.org/abs/2406.09029
Autor:
Wei, Ran, Foster, Simon, Mei, Haitao, Yan, Fang, Yang, Ruizhe, Habli, Ibrahim, O'Halloran, Colin, Tudor, Nick, Kelly, Tim, Nemouchi, Yakoub
Assurance cases are used to communicate and assess confidence in critical system properties such as safety and security. Historically, assurance cases have been manually created documents, which are evaluated by system stakeholders through lengthy an
Externí odkaz:
http://arxiv.org/abs/2403.15236
Autor:
Porter, Zoe, Ryan, Philippa, Morgan, Phillip, Al-Qaddoumi, Joanna, Twomey, Bernard, McDermid, John, Habli, Ibrahim
It is widely acknowledged that we need to establish where responsibility lies for the outputs and impacts of AI-enabled systems. But without a clear and precise understanding of what "responsibility" means, deliberations about where responsibility li
Externí odkaz:
http://arxiv.org/abs/2308.02608
Autor:
Kaas, Marten H. L., Porter, Zoe, Lim, Ernest, Higham, Aisling, Khavandi, Sarah, Habli, Ibrahim
Publikováno v:
TAS 2023: Proceedings of the First International Symposium on Trustworthy Autonomous Systems
The deployment and use of AI systems should be both safe and broadly ethically acceptable. The principles-based ethics assurance argument pattern is one proposal in the AI ethics landscape that seeks to support and achieve that aim. The purpose of th
Externí odkaz:
http://arxiv.org/abs/2305.14182
Autor:
Abeywickrama, Dhaminda B., Wilson, James, Lee, Suet, Chance, Greg, Winter, Peter D., Manzini, Arianna, Habli, Ibrahim, Windsor, Shane, Hauert, Sabine, Eder, Kerstin
The behaviours of a swarm are not explicitly engineered. Instead, they are an emergent consequence of the interactions of individual agents with each other and their environment. This emergent functionality poses a challenge to safety assurance. The
Externí odkaz:
http://arxiv.org/abs/2302.10292
In recent years, the number of machine learning (ML) technologies gaining regulatory approval for healthcare has increased significantly allowing them to be placed on the market. However, the regulatory frameworks applied to them were originally devi
Externí odkaz:
http://arxiv.org/abs/2209.00421
Autor:
Hawkins, Richard, Osborne, Matt, Parsons, Mike, Nicholson, Mark, McDermid, John, Habli, Ibrahim
Autonomous systems (AS) are systems that have the capability to take decisions free from direct human control. AS are increasingly being considered for adoption for applications where their behaviour may cause harm, such as when used for autonomous d
Externí odkaz:
http://arxiv.org/abs/2208.00853