Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

9

AGI
2015

favoriteEmaildiscussreport

16views Artificial Intelligence» more AGI 2015»

Inferring Human Values for Safe AGI Design

8 years 14 days ago

Inferring Human Values for Safe AGI Design

Download agi-conf.org

Abstract. Aligning goals of superintelligent machines with human values is one of the ways to pursue safety in AGI systems. To achieve this, it is ﬁrst necessary to learn what human values are. However, human values are incredibly complex and cannot easily be formalized by hand. In this work, we propose a general framework to estimate the values of a human given its behavior.

Can Eren Sezener

Real-time Traffic

AGI 2015 | Artificial Intelligence |

claim paper

Related Content

» Open Source AI

» Design of a safe computersupported cooperative environment in radiotherapy exploratory ide...

» Improving the safety of homeless young people with mobile phones values form and function

» Foundations of Human Computing Facial Expression and Emotion

» Social coding in GitHub transparency and collaboration in an open software repository

» The design and evaluation of an enduserdeployable whole house contactless power consumptio...

» BALANCE towards a usable pervasive wellness application with accurate activity inference

» DySy dynamic symbolic execution for invariant inference

» Inferring Piecewise Ancestral History from Haploid Sequences

» Enhancing independence and safety for blind and deafblind public transit riders

Post Info
More Details (n/a)

Added	13 Apr 2016
Updated	13 Apr 2016
Type	Journal
Year	2015
Where	AGI
Authors	Can Eren Sezener

Comments (0)