책 이미지
책 정보
· 분류 : 외국도서 > 컴퓨터 > 인공지능(AI)
· ISBN : 9780815369820
· 쪽수 : 444쪽
· 출판일 : 2018-08-23
목차
Preface: Introduction to Artificial Intelligence Safety and Security
Roman V. Yampolskiy
Part I: Concerns of Luminaries
1. Why the Future Doesn't Need Us
Bill Joy
2. The Deeply Intertwined Promise and Peril of GNR
Ray Kurzweil
3. The Basic AI Drives
Stephen M. Omohundro
4. The Ethics of Artificial Intelligence
Nick Bostrom and Eliezer Yudkowsky
5. Friendly Artificial Intelligence: the Physics Challenge
Max Tegmark
6. Exploring strategies for safe access to superintelligent problem-solving capabilities
K. Eric Drexler
7. The Value Learning Problem
Nate Soares
8. Adversarial Examples in the Physical World
Alexey Kurakin, Ian J. Goodfellow, Samy Bengio
9. How Might AI Come About?
David Brin
10. The MADCOM Future
Matt Chessen
11. Strategic Implications of Openness in AI Development
Nick Bostrom
Part II: Responses of Scholars
12. Using Human History, Psychology and Biology to Make AI Safe for Humans
Gus Bekdash
13. AI Safety: A First-Person Perspective
Edward Frenkel
14. Strategies for an Unfriendly Oracle AI with Reset Button
Olle Haggstrom
15. Goal Changes in Intelligent Agents
Seth Herd, Stephen J. Read, Randall O’Reilly and David Jilk
16. Limits to Verification and Validation of Agentic Behavior
Dave Jilk
17. Adversarial Machine Learning
Phillip Kuznetsov, Riley Edmunds, Ted Xiao, Humza Iqbal, Raul Puri, Noah Golmant, Shannon Shih
18. Value Alignment Via Tractable Preference Distance
Andrea Loreggia, Nicholas Mattei, Francesca Rossi, K. Brent Venable
19. A Rationally Addicted Artificial Superintelligence
James Miller
20. On the Security of Robotic Applications using ROS
David Portugal, Miguel A. Santosy, Samuel Pereira, Micael S. Couceiro
21. Social Choice and the Value Alignment Problem
Mahendra Prasad
22. Disjunctive scenarios of catastrophic AI risk
Kaj Sotala
23. Artificial Intelligence and Global Hegemony
Maurizio Tinnirello
24. Superintelligence and the Future of Governance
Phil Torres
25. Military AI as a Convergent Goal of Self-Improving AI
Alexey Turchin and David Denkenberger
26. A Value-Sensitive Design Approach to Intelligent Agents
Steven Umbrello & Angelo DeBellis
27. Consequentialism, Deontology, and Artificial Intelligence Safety
Mark Walker
28. Smart Machines ARE a Threat to Humanity
Kevin Warwick
