HOME > 상세정보

상세정보

Human compatible : artificial intelligence and the problem of control

Human compatible : artificial intelligence and the problem of control (2회 대출)

자료유형
단행본
개인저자
Russell, Stuart J. (Stuart Jonathan).
서명 / 저자사항
Human compatible : artificial intelligence and the problem of control / Stuart Russell.
발행사항
[New York] :   Viking,   c2019.  
형태사항
xii, 336 p. ; 24 cm.
ISBN
9780525558613 (hardcover)
요약
"In the popular imagination, superhuman artificial intelligence is an approaching tidal wave that threatens not just jobs and human relationships, but civilization itself. Conflict between humans and machines is seen as inevitable and its outcome all too predictable. In this groundbreaking book, distinguished AI researcher Stuart Russell argues that this scenario can be avoided, but only if we rethink AI from the ground up. Russell begins by exploring the idea of intelligence in humans and in machines. He describes the near-term benefits we can expect, from intelligent personal assistants to vastly accelerated scientific research, and outlines the AI breakthroughs that still have to happen before we reach superhuman AI. He also spells out the ways humans are already finding to misuse AI, from lethal autonomous weapons to viral sabotage. If the predicted breakthroughs occur and superhuman AI emerges, we will have created entities far more powerful than ourselves. How can we ensure they never, ever, have power over us? Russell suggests that we can rebuild AI on a new foundation, according to which machines are designed to be inherently uncertain about the human preferences they are required to satisfy. Such machines would be humble, altruistic, and committed to pursue our objectives, not theirs. This new foundation would allow us to create machines that are provably deferential and provably beneficial. In a 2014 editorial co-authored with Stephen Hawking, Russell wrote, "Success in creating AI would be the biggest event in human history. Unfortunately, it might also be the last." Solving the problem of control over AI is not just possible; it is the key that unlocks a future of unlimited promise"--
서지주기
Includes bibliographical references and index.
일반주제명
Automation --Safety measures. Artificial intelligence --Social aspects. Artificial intelligence --Accidents --Risk assessment.
000 00000cam u2200205 a 4500
001 000046003986
005 20191031161453
008 191031s2019 nyu b 001 0 eng d
010 ▼a 2019029688
020 ▼a 9780525558613 (hardcover)
020 ▼z 9780525558620 (ebook)
035 ▼a (KERIS)REF000019081537
040 ▼a DLC ▼b eng ▼e rda ▼c DLC ▼d 211009
050 0 0 ▼a Q334.7 ▼b .R87 2019
082 0 0 ▼a 006.301 ▼2 23
084 ▼a 006.301 ▼2 DDCK
090 ▼a 006.301 ▼b R967h
100 1 ▼a Russell, Stuart J. ▼q (Stuart Jonathan).
245 1 0 ▼a Human compatible : ▼b artificial intelligence and the problem of control / ▼c Stuart Russell.
260 ▼a [New York] : ▼b Viking, ▼c c2019.
300 ▼a xii, 336 p. ; ▼c 24 cm.
504 ▼a Includes bibliographical references and index.
520 ▼a "In the popular imagination, superhuman artificial intelligence is an approaching tidal wave that threatens not just jobs and human relationships, but civilization itself. Conflict between humans and machines is seen as inevitable and its outcome all too predictable. In this groundbreaking book, distinguished AI researcher Stuart Russell argues that this scenario can be avoided, but only if we rethink AI from the ground up. Russell begins by exploring the idea of intelligence in humans and in machines. He describes the near-term benefits we can expect, from intelligent personal assistants to vastly accelerated scientific research, and outlines the AI breakthroughs that still have to happen before we reach superhuman AI. He also spells out the ways humans are already finding to misuse AI, from lethal autonomous weapons to viral sabotage. If the predicted breakthroughs occur and superhuman AI emerges, we will have created entities far more powerful than ourselves. How can we ensure they never, ever, have power over us? Russell suggests that we can rebuild AI on a new foundation, according to which machines are designed to be inherently uncertain about the human preferences they are required to satisfy. Such machines would be humble, altruistic, and committed to pursue our objectives, not theirs. This new foundation would allow us to create machines that are provably deferential and provably beneficial. In a 2014 editorial co-authored with Stephen Hawking, Russell wrote, "Success in creating AI would be the biggest event in human history. Unfortunately, it might also be the last." Solving the problem of control over AI is not just possible; it is the key that unlocks a future of unlimited promise"-- ▼c Provided by publisher.
650 0 ▼a Automation ▼x Safety measures.
650 0 ▼a Artificial intelligence ▼x Social aspects.
650 0 ▼a Artificial intelligence ▼x Accidents ▼x Risk assessment.
945 ▼a KLPA

소장정보

No. 소장처 청구기호 등록번호 도서상태 반납예정일 예약 서비스
No. 1 소장처 과학도서관/Sci-Info(2층서고)/ 청구기호 006.301 R967h 등록번호 121250803 도서상태 대출가능 반납예정일 예약 서비스 B M

컨텐츠정보

목차

Preface	p. xi
Chapter 1	If We Succeed	p. 1
Chapter 2	Intelligence in Humans and Machines	p. 13
Chapter 3	How Might Al Progress in the Future?	p. 62
Chapter 4	Misuses of Al	p. 103
Chapter 5	Overly Intelligent Al	p. 132
Chapter 6	The Not-So-Great Al Debate	p. 145
Chapter 7	Al: A Different Approach	p. 171
Chapter 8	Provably Beneficial Al	p. 184
Chapter 9	Complications: Us	p. 211
Chapter 10	Problem Solved?	p. 246
Appendix A	Searching for Solutions	p. 257
Appendix B	Knowledge and Logic	p. 267
Appendix C	Uncertainty and Probability	p. 273
Appendix D	Learning from Experience

관련분야 신착자료

Deisenroth, Marc Peter (2020)
National Academies of Sciences, Engineering, and Medicine (U.S.) (2020)