Software quality assurance increasingly depends on the ability to combine automated testing with data-driven estimates of defect risk. Conventional test suites reveal failures in executed scenarios but do not necessarily identify which untested changes are most likely to introduce faults. Machine learning models can pr...
F. Doshi-Velez· Computer Science Bulletin· 0 citations
We explored the feasibility of predicting, using individually-tailored artificial intelligence (AI) models, substance use and craving from Fitbit data collected in free-living conditions. Most substances examined acutely raise heart rate, and craving is known to often involve autonomic arousal. Because heart rate res...
Ali Kargarandehkordi, Agnik Banerjee, Yi-Nan Sun et al.· npj Biosensing· 0 citations
Ref referential uncertainty is studied in a collaborative puzzle task where a human Helper instructs an AI Worker to place pieces, showing that a separately elicited belief distribution over candidate pieces is better calibrated and better discriminates correct from incorrect placements than raw action-token probabilit...
Christian Pölitz, F. Doshi-Velez, Siân Lindley· arXiv.org· 0 citations
This work designed two scaffolded interfaces around the same negotiation scaffold: one presented a completed AI analysis, while the other supported user-directed, incremental development, which elicited a broader repertoire of analytic requests and lower subjective effort.
Zi-Lin Ma, Suzi Jazmati, Marco Chimenton et al.· 0 citations
It is shown that, when agent utilities can be expressed linearly in a fixed feature representation, the alignment problem can be reformulated as linear optimization over a convex impact space, which makes it amenable to the standard toolkit of welfare economics and mechanism design.
Zachary Wojtowicz, Michelle Si, F. Doshi-Velez et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.