02048nam a2200385 i 4500999001700000001000600017003000900023005001700032008004100049010001700090020004600107020004700153040003800200042000800238050002100246082001400267245008100281250001900362260006000381300004700441490006700488500002900555504005000584520054700634526000801181650004001189650004201229650005301271650006301324650002901387700004201416852004001458942001201498952015201510  c40451d4045134324BD-DhAAL20211110164252.0190320t2019    flua     b    001 0 eng    a  2018015502  a9781138320840 (hardback : acidfree paper)  a9780815369820 (paperback : acidfree paper)  aDLCbengcDLCerdadDLCdBD-DhAAL  apcc00aT59.5b.A76 201900a006.322300aArtificial intelligence safety and security /cedited by Roman V. Yampolskiy  aFirst edition.  aBoca Raton :bCRC Press, Taylor & Francis Group,cc2019  axxix, 443 pages :billustrations ;c25 cm.0 aChapman & Hall/CRC artificial intelligence and robotics series  a"A Chapman & Hall book."  aIncludes bibliographical references and index  aThis book includes chapters from leading AI Safety researchers, addressing different aspects of the AI control problem as it relates to the development of safe and secure artificial intelligence. The book would be the first to address challenges of constructing safe and secure artificially intelligent systems. No similar book currently exists that concentrates on technical aspects of this research from the computer science point of view. Competing books are aimed at general/non-professional audiences from a philosophical point of view--  aCSE 0aAutomationxSafety measures.930295 0aAutomationxSecurity measures.930296 0aArtificial intelligencexSafety measures.930297 0aArtificial intelligencexMoral and ethical aspects.930298 0aComputer science.9424921 aYampolskiy, Roman V.,eeditor.930299  aAyesha Abed LibrarycGeneral Stacks  2ddccBK  00102ddc4070aBRACULbBRACULcGENd2019-02-26eParamag3336.29l7m41o006.3 ARTp3010034324r2025-08-31s2025-08-17t1v3336.29w2019-02-26yBK