Articoli correlati a The Alignment Problem: How Can Machines Learn Human...

The Alignment Problem: How Can Machines Learn Human Values? - Rilegato

 
9781786494306: The Alignment Problem: How Can Machines Learn Human Values?

Al momento non sono disponibili copie per questo codice ISBN.

Sinossi

'Vital reading. This is the book on artificial intelligence we need right now.' Mike Krieger, cofounder of Instagram

Artificial intelligence is rapidly dominating every aspect of our modern lives influencing the news we consume, whether we get a mortgage, and even which friends wish us happy birthday. But as algorithms make ever more decisions on our behalf, how do we ensure they do what we want? And fairly?

This conundrum - dubbed 'The Alignment Problem' by experts - is the subject of this timely and important book. From the AI program which cheats at computer games to the sexist algorithm behind Google Translate, bestselling author Brian Christian explains how, as AI develops, we rapidly approach a collision between artificial intelligence and ethics. If we stand by, we face a future with unregulated algorithms that propagate our biases - and worse - violate our most sacred values. Urgent and fascinating, this is an accessible primer to the most important issue facing AI researchers today.

Le informazioni nella sezione "Riassunto" possono far riferimento a edizioni diverse di questo titolo.

Dalla quarta di copertina

Artificial intelligence is rapidly dominating every aspect of our modern lives influencing the news we consume, whether we get a mortgage, and even which friends wish us happy birthday. But as algorithms make ever more decisions on our behalf, how do we ensure they do what we want? And fairly? This conundrum - dubbed 'The Alignment Problem' by experts - is the subject of this timely and important book. From the AI program which cheats at computer games to the sexist algorithm behind Google Translate, bestselling author Brian Christian explains how, as AI develops, we rapidly approach a collision between artificial intelligence and ethics. If we stand by, we face a future with unregulated algorithms that propagate our biases - and worse - violate our most sacred values. Urgent and fascinating, this is an accessible primer to the most important issue facing AI researchers today.

Le informazioni nella sezione "Su questo libro" possono far riferimento a edizioni diverse di questo titolo.

  • EditoreFaber and Faber
  • Data di pubblicazione2021
  • ISBN 10 1786494302
  • ISBN 13 9781786494306
  • RilegaturaCopertina rigida
  • LinguaInglese
  • Numero edizione1
  • Numero di pagine496
  • Contatto del produttorenon disponibile

(nessuna copia disponibile)

Cerca:



Inserisci un desiderata

Non riesci a trovare il libro che stai cercando? Continueremo a cercarlo per te. Se uno dei nostri librai lo aggiunge ad AbeBooks, ti invieremo una notifica!

Inserisci un desiderata

Altre edizioni note dello stesso titolo

9781786494337: The Alignment Problem: How Can Machines Learn Human Values?

Edizione in evidenza

ISBN 10:  1786494337 ISBN 13:  9781786494337
Casa editrice: Atlantic Books, 2021
Brossura