Human compatible : artificial intelligence and the problem of control

Zugang

Weitere Informationen sehen Sie, wenn Sie angemeldet sind. Noch keinen Account? Jetzt registrieren.

Zusammenfassung: If we succeed --Intelligence in humans and machines --How might AI progress in the future? --Misuses of AI --Overly intelligent AI --The not-so-great AI debate --AI : a different approach --Provably beneficial AI --Complications : us --Problem solved? --Searching for solutions --Knowledge and logic --Uncertainty and probability --Learning from experience
In the popular imagination, conflict between humans and machines is seen as inevitable and its outcome all too predictable. Russell argues that this scenario can be avoided, but only if we rethink AI from the ground up. He explores the idea of intelligence in humans and in machines, describes the near-term benefits we can expect from intelligent personal assistants and accelerated scientific research, and outlines the AI breakthroughs that still have to happen before we reach superhuman AI. Russell also spells out the ways humans are already misusing AI, from lethal autonomous weapons to viral sabotage. -- adapted from jacket
Umfang: xiv, 336 Seiten; Illustrationen; 22 cm
Sprache: Englisch
Schlagworte: Künstliche Intelligenz > Automation > Risikoanalyse > Sicherheitsmaßnahme
BK-Notation: 54.72 Künstliche Intelligenz
ISBN: 0525558632
9780525558637