e-branch	Login My List - 0 Help
	Home   My Account/Renew Loans   Community Info   KidSearch   New Catalogue!

Search Advanced By Format By Number My Searches Can't Find it? Find Magazine Articles & more Problems?

Search:  Title Starts with...Title Keyword(s)Author/Performer/Name (Last,First)Author/Performer/Name Keyword(s)Subject Starts with...Subject Keyword(s)Series Starts with...Series Keyword(s)Anyword/AnywhereList Name Keyword(s)       Refine Search     > You're searching: Halifax Public Libraries

Item Information   Copy / Holding Information     Publisher Weekly Review     More Content       More by this author     Christian, Brian, 1984-     Subjects     Artificial intelligence -- Moral and ethical aspects.     Artificial intelligence -- Social aspects.     Machine learning -- Safety measures.     Artificial intelligence -- Risk assessment.     Software failures.     Social values.     Artificial intelligence.     Machine learning.     Browse Catalog     by author:      Christian, Brian, 1984-       by title:      The alignment proble...       by call number:      006.31019 C555a     Search the Web     Christian, Brian, 1984-     Artificial intelligence -- Moral and ethical aspects.     Artificial intelligence -- Social aspects.     Machine learning -- Safety measures.     Artificial intelligence -- Risk assessment.     Software failures.     Social values.     Artificial intelligence.     Machine learning.       MARC Display

The alignment problem : machine learning and human values / Brian Christian. by Christian, Brian, 1984- W.W. Norton & Company, 2020. Call #: 006.31019 C555a Subjects Artificial intelligence -- Moral and ethical aspects.   Artificial intelligence -- Social aspects.   Machine learning -- Safety measures.   Artificial intelligence -- Risk assessment.   Software failures.   Social values.   Artificial intelligence.   Machine learning. ISBN:  9780393635829 (hc.) Alternate title:  Machine learning and human values Edition:  1st ed. Description:  xii, 476 p. ; 25 cm. Bibliography:  Includes bibliographical references (pages [401]-451) and index. Summary:  "A jaw-dropping exploration of everything that goes wrong when we build AI systems-and the movement to fix them. Today's 'machine-learning' systems, trained by data, are so effective that we've invited them to see and hear for us -- and to make decisions on our behalf. But alarm bells are ringing. Systems cull résumés until, years later, we discover that they have inherent gender biases. Algorithms decide bail and parole -- and appear to assess black and white defendants differently. We can no longer assume that our mortgage application, or even our medical tests, will be seen by human eyes. And autonomous vehicles on our streets can injure or kill. When systems we attempt to teach will not, in the end, do what we want or what we expect, ethical and potentially existential risks emerge. Researchers call this the alignment problem. In best-selling author Brian Christian's riveting account, we meet the alignment problem's 'first-responders,' and learn their ambitious plan to solve it before our hands are completely off the wheel."--From publisher. Holds:  1   Copy/Holding information Location Collection Call No. Item type Status Due Date   Woodlawn Public Library Adult Nonfiction 006.31019 C555a Adult books Item being held   Add Copy to MyList Central Library Adult Nonfiction 006.31019 C555a Core Collection - Adult Checked out Jul 19, 2024 Add Copy to MyList

Horizon Information Portal 3.24_8902M

© 2001-2013 SirsiDynix All rights reserved.