The alignment problem: how can machines learn human values

The author explains how, as machine learning develops, we rapidly approach a collision between artificial intelligence and our most sacred values. Unpicking the latest studies and featuring numerous interviews with top researchers he asks profound questions about learning and intelligence: for both...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Christian, Brian 1984- (VerfasserIn)
Format: Elektronisch E-Book
Sprache:English
Veröffentlicht: London Atlantic Books 2020
Schlagworte:
Online-Zugang:TUM01
UBG01
Zusammenfassung:The author explains how, as machine learning develops, we rapidly approach a collision between artificial intelligence and our most sacred values. Unpicking the latest studies and featuring numerous interviews with top researchers he asks profound questions about learning and intelligence: for both humans and computers
Beschreibung:1 Online-Ressource (xii, 476 Seiten)
ISBN:9781786494320
1786494310

Es ist kein Print-Exemplar vorhanden.

Fernleihe Bestellen Achtung: Nicht im THWS-Bestand!