publication . Article . 2017

Steps Toward Robust Artificial Intelligence

Thomas G. Dietterich;
Open Access
  • Published: 02 Oct 2017 Journal: AI Magazine, volume 38, pages 3-24 (issn: 0738-4602, eissn: 2371-9621, Copyright policy)
  • Publisher: Association for the Advancement of Artificial Intelligence (AAAI)
Abstract
<jats:p>Recent advances in artificial intelligence are encouraging governments and corporations to deploy AI in high-stakes settings including driving cars autonomously, managing the power grid, trading on stock exchanges, and controlling autonomous weapons systems. Such applications require AI methods to be robust to both the known unknowns (those uncertain aspects of the world about which the computer can reason explicitly) and the unknown unknowns (those aspects of the world that are not captured by the system’s models). This article discusses recent progress in AI and then describes eight ideas related to robustness that are being pursued within the AI resea...
Subjects
ACM Computing Classification System: GeneralLiterature_MISCELLANEOUS
free text keywords: Artificial Intelligence, Computer science, business.industry, business, Finite system, Research community, Stock exchange, Power grid, Robustness (computer science)
Download fromView all 2 versions
AI Magazine
Article
Provider: UnpayWall
AI Magazine
Article . 2017
Provider: AI Magazine
AI Magazine
Article . 2017
Provider: Crossref
Any information missing or wrong?Report an Issue