Sinossi
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. Recent years have seen an eruption of concern as the field of machine learning advances. When the 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.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 as autonomous vehicles share our streets, we are increasingly putting our lives in their hands.The mathematical and computational models driving these changes range in complexity from something that can fit on a spreadsheet to a complex system that might credibly be called “artificial intelligence.” They are steadily replacing both human judgment and explicitly programmed software.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. In a masterful blend of history and on-the ground reporting, Christian traces the explosive growth in the field of machine learning and surveys its current, sprawling frontier. Readers encounter a discipline finding its legs amid exhilarating and sometimes terrifying progress. Whether they—and we—succeed or fail in solving the alignment problem will be a defining human story.The Alignment Problem
Le informazioni nella sezione "Riassunto" possono far riferimento a edizioni diverse di questo titolo.
Altre edizioni note dello stesso titolo
Risultati della ricerca per The Alignment Problem: Machine Learning and Human Values
Foto dell'editore
The Alignment Problem: Machine Learning and Human Values
Editore:
W. W. Norton & Company, 2021
ISBN 10: 0393868338
ISBN 13: 9780393868333
Antico o usato
paperback
Da: HPB-Ruby, Dallas, TX, U.S.A.
Valutazione del venditore 5 su 5 stelle
paperback. Condizione: Very Good. Connecting readers with great books since 1972! Used books may not include companion materials, and may have some shelf wear or limited writing. We ship orders daily and Customer Service is our top priority! Codice articolo S_471282075
Compra usato
EUR 10,07
Spedizione EUR 3,22
Spedito in U.S.A.
Spedito in U.S.A.
Quantità: 1 disponibili
Foto dell'editore
The Alignment Problem: Machine Learning and Human Values
Da: Lakeside Books, Benton Harbor, MI, U.S.A.
Valutazione del venditore 5 su 5 stelle
Condizione: New. Brand New! Not Overstocks or Low Quality Book Club Editions! Direct From the Publisher! We're not a giant, faceless warehouse organization! We're a small town bookstore that loves books and loves it's customers! Buy from Lakeside Books! Codice articolo OTF-S-9780393868333
Compra nuovo
EUR 11,93
Spedizione EUR 3,42
Spedito in U.S.A.
Spedito in U.S.A.
Quantità: Più di 20 disponibili
Immagini fornite dal venditore
Alignment Problem : Machine Learning and Human Values
Da: GreatBookPrices, Columbia, MD, U.S.A.
Valutazione del venditore 5 su 5 stelle
Condizione: New. Codice articolo 42563755-n
Compra nuovo
EUR 13,11
Spedizione EUR 2,26
Spedito in U.S.A.
Spedito in U.S.A.
Quantità: Più di 20 disponibili
Foto dell'editore
The Alignment Problem: Machine Learning and Human Values Format: Paperback
Da: INDOO, Avenel, NJ, U.S.A.
Valutazione del venditore 5 su 5 stelle
Condizione: New. Brand New. Codice articolo 9780393868333
Compra nuovo
EUR 16,27
Spedizione gratuita
Spedito in U.S.A.
Spedito in U.S.A.
Quantità: Più di 20 disponibili
Immagini fornite dal venditore
Alignment Problem : Machine Learning and Human Values
Editore:
W. W. Norton & Company, 2021
ISBN 10: 0393868338
ISBN 13: 9780393868333
Antico o usato
Brossura
Da: GreatBookPrices, Columbia, MD, U.S.A.
Valutazione del venditore 5 su 5 stelle
Condizione: As New. Unread book in perfect condition. Codice articolo 42563755
Compra usato
EUR 14,74
Spedizione EUR 2,26
Spedito in U.S.A.
Spedito in U.S.A.
Quantità: Più di 20 disponibili
Immagini fornite dal venditore
The Alignment Problem
Da: Rarewaves USA, OSWEGO, IL, U.S.A.
Valutazione del venditore 5 su 5 stelle
Paperback. Condizione: New. 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. Recent years have seen an eruption of concern as the field of machine learning advances. When the 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.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 as autonomous vehicles share our streets, we are increasingly putting our lives in their hands.The mathematical and computational models driving these changes range in complexity from something that can fit on a spreadsheet to a complex system that might credibly be called "artificial intelligence." They are steadily replacing both human judgment and explicitly programmed software.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. In a masterful blend of history and on-the ground reporting, Christian traces the explosive growth in the field of machine learning and surveys its current, sprawling frontier. Readers encounter a discipline finding its legs amid exhilarating and sometimes terrifying progress. Whether they-and we-succeed or fail in solving the alignment problem will be a defining human story.The Alignment Problem offers an unflinching reckoning with humanity's biases and blind spots, our own unstated assumptions and often contradictory goals. A dazzlingly interdisciplinary work, it takes a hard look not only at our technology but at our culture-and finds a story by turns harrowing and hopeful. Codice articolo LU-9780393868333
Compra nuovo
EUR 17,61
Spedizione gratuita
Spedito in U.S.A.
Spedito in U.S.A.
Quantità: Più di 20 disponibili
Foto dell'editore
The Alignment Problem: Machine Learning and Human Values
Da: California Books, Miami, FL, U.S.A.
Valutazione del venditore 4 su 5 stelle
Condizione: New. Codice articolo I-9780393868333
Compra nuovo
EUR 17,66
Spedizione gratuita
Spedito in U.S.A.
Spedito in U.S.A.
Quantità: Più di 20 disponibili
Foto dell'editore
The Alignment Problem: Machine Learning and Human Values
Da: Lucky's Textbooks, Dallas, TX, U.S.A.
Valutazione del venditore 5 su 5 stelle
Condizione: New. Codice articolo ABLIING23Feb2215580178907
Compra nuovo
EUR 14,53
Spedizione EUR 3,42
Spedito in U.S.A.
Spedito in U.S.A.
Quantità: Più di 20 disponibili
Immagini fornite dal venditore
The Alignment Problem (Paperback)
Da: Grand Eagle Retail, Bensenville, IL, U.S.A.
Valutazione del venditore 5 su 5 stelle
Paperback. Condizione: new. Paperback. Todays machine-learning systems, trained by data, are so effective that weve invited them to see and hear for usand to make decisions on our behalf. But alarm bells are ringing. Recent years have seen an eruption of concern as the field of machine learning advances. When the 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.Systems cull resumes until, years later, we discover that they have inherent gender biases. Algorithms decide bail and paroleand 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 as autonomous vehicles share our streets, we are increasingly putting our lives in their hands.The mathematical and computational models driving these changes range in complexity from something that can fit on a spreadsheet to a complex system that might credibly be called artificial intelligence. They are steadily replacing both human judgment and explicitly programmed software.In best-selling author Brian Christians riveting account, we meet the alignment problems first-responders, and learn their ambitious plan to solve it before our hands are completely off the wheel. In a masterful blend of history and on-the ground reporting, Christian traces the explosive growth in the field of machine learning and surveys its current, sprawling frontier. Readers encounter a discipline finding its legs amid exhilarating and sometimes terrifying progress. Whether theyand wesucceed or fail in solving the alignment problem will be a defining human story.The Alignment Problem offers an unflinching reckoning with humanitys biases and blind spots, our own unstated assumptions and often contradictory goals. A dazzlingly interdisciplinary work, it takes a hard look not only at our technology but at our cultureand finds a story by turns harrowing and hopeful. "If youre going to read one book on artificial intelligence, this is the one." Stephen Marche, New York TimesA jaw-dropping exploration of everything that goes wrong when we build AI systems and the movement to fix them. Shipping may be from multiple locations in the US or from the UK, depending on stock availability. Codice articolo 9780393868333
Compra nuovo
EUR 18,49
Spedizione gratuita
Spedito in U.S.A.
Spedito in U.S.A.
Quantità: 1 disponibili
Immagini fornite dal venditore
The Alignment Problem
Da: Rarewaves.com USA, London, LONDO, Regno Unito
Valutazione del venditore 5 su 5 stelle
Paperback. Condizione: New. 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. Recent years have seen an eruption of concern as the field of machine learning advances. When the 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.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 as autonomous vehicles share our streets, we are increasingly putting our lives in their hands.The mathematical and computational models driving these changes range in complexity from something that can fit on a spreadsheet to a complex system that might credibly be called "artificial intelligence." They are steadily replacing both human judgment and explicitly programmed software.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. In a masterful blend of history and on-the ground reporting, Christian traces the explosive growth in the field of machine learning and surveys its current, sprawling frontier. Readers encounter a discipline finding its legs amid exhilarating and sometimes terrifying progress. Whether they-and we-succeed or fail in solving the alignment problem will be a defining human story.The Alignment Problem offers an unflinching reckoning with humanity's biases and blind spots, our own unstated assumptions and often contradictory goals. A dazzlingly interdisciplinary work, it takes a hard look not only at our technology but at our culture-and finds a story by turns harrowing and hopeful. Codice articolo LU-9780393868333
Compra nuovo
EUR 21,78
Spedizione gratuita
Spedito da Regno Unito a U.S.A.
Spedito da Regno Unito a U.S.A.
Quantità: Più di 20 disponibili