Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Balayan, Vladimir"'
Autor:
Amarasinghe, Kasun, Rodolfa, Kit T., Jesus, Sérgio, Chen, Valerie, Balayan, Vladimir, Saleiro, Pedro, Bizarro, Pedro, Talwalkar, Ameet, Ghani, Rayid
Most existing evaluations of explainable machine learning (ML) methods rely on simplifying assumptions or proxies that do not reflect real-world use cases; the handful of more robust evaluations on real-world settings have shortcomings in their desig
Externí odkaz:
http://arxiv.org/abs/2206.13503
Concept-based explanations aims to fill the model interpretability gap for non-technical humans-in-the-loop. Previous work has focused on providing concepts for specific models (eg, neural networks) or data types (eg, images), and by either trying to
Externí odkaz:
http://arxiv.org/abs/2205.03601
In ML-aided decision-making tasks, such as fraud detection or medical diagnosis, the human-in-the-loop, usually a domain-expert without technical ML knowledge, prefers high-level concept-based explanations instead of low-level explanations based on m
Externí odkaz:
http://arxiv.org/abs/2104.12459
Autor:
Jesus, Sérgio, Belém, Catarina, Balayan, Vladimir, Bento, João, Saleiro, Pedro, Bizarro, Pedro, Gama, João
There have been several research works proposing new Explainable AI (XAI) methods designed to generate model explanations having specific properties, or desiderata, such as fidelity, robustness, or human-interpretability. However, explanations are se
Externí odkaz:
http://arxiv.org/abs/2101.08758
Machine Learning (ML) has been increasingly used to aid humans to make better and faster decisions. However, non-technical humans-in-the-loop struggle to comprehend the rationale behind model predictions, hindering trust in algorithmic decision-makin
Externí odkaz:
http://arxiv.org/abs/2012.01932
In ML-aided decision-making tasks, such as fraud detection or medical diagnosis, the human-in-the-loop, usually a domain-expert without technical ML knowledge, prefers high-level concept-based explanations instead of low-level explanations based on m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cf1159975c81940cd0a2ddf7da847643
http://arxiv.org/abs/2104.12459
http://arxiv.org/abs/2104.12459
Autor:
Balayan, Vladimir
Publikováno v:
Repositório Científico de Acesso Aberto de Portugal
Repositório Científico de Acesso Aberto de Portugal (RCAAP)
instacron:RCAAP
Repositório Científico de Acesso Aberto de Portugal (RCAAP)
instacron:RCAAP
Machine Learning (ML) has been increasingly used to aid humans making high-stakes decisions in a wide range of areas, from public policy to criminal justice, education, healthcare, or financial services. However, it is very hard for humans to grasp t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::ac024887bd351b0e007d865c89dab544
https://hdl.handle.net/10362/130774
https://hdl.handle.net/10362/130774