The alignment problem : machine learning and human values / Brian Christian.

By:

Christian, Brian, 1984-

Publisher: New York : W.W. Norton & Company, [2020]Edition: First editionDescription: xii, 476 pages ; 25 cmContent type:

text

Media type:

unmediated

Carrier type:

volume

ISBN:

0393635821
9780393635829

Subject(s):

DDC classification:

174/.90063 23

LOC classification:

Q334.7 .C47 2020

Contents:

Prophecy. Representation ; Fairness ; Transparency -- Agency. Reinforcement ; Shaping ; Curiosity -- Normativity. Imitation ; Inference ; Uncertainty.

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."-- Provided by publisher.

Holdings ( 1 )
Title notes ( 3 )

Holdings
Item type	Current library	Shelving location	Call number	Copy number	Status	Date due	Barcode
Book	NMC Library	Stacks	Q334.7 .C47 2020 (Browse shelf(Opens below))	1	Available		33039001511608

Browsing NMC Library shelves, Shelving location: Stacks Close shelf browser (Hides shelf browser)

Previous								Next
Previous	Q183.3. A1 R828 2019 How we teach science : what's changed, and why it matters /	Q295 .A443 2022 Earthly order : how natural laws define human life /	Q310 .C38 2018 An illustrated dictionary of cyborg anthropology /	Q334.7 .C47 2020 The alignment problem : machine learning and human values /	Q335 .B377 2013 Our final invention : artificial intelligence and the end of the human era /	Q335 .B7 2007 Introducing artificial intelligence /	Q335 .C63 2021 Atlas of AI : power, politics, and the planetary costs of artificial intelligence /	Next

Includes bibliographical references and index.

Prophecy. Representation ; Fairness ; Transparency -- Agency. Reinforcement ; Shaping ; Curiosity -- Normativity. Imitation ; Inference ; Uncertainty.

"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."-- Provided by publisher.