Your browser doesn't support the features required by impress.js, so you are presented with a simplified version of this presentation.

For the best experience please use the latest Chrome, Safari or Firefox browser.

Introduction to Moral Induction Model and its Deployment in Artificial Agents


Daniel D. Hromada & Ilaria Gaudiello
Artificial Autonomous Agent Turing Test Hierarchy
(Hromada, 2012, AISB/IACAP)
AAA
CO
COrporal Cluster Turing Test subHierarchy
organic
spatial
sexual
SE
SEnsual Cluster Turing Test subHierarchy
visual
logical
musical
BA
BAbbling Cluster Turing Test subHierarchy
emotion
lingua
moral
Grammar induction


BA
BAbbling Cluster Turing Test subHierarchy
emotion
lingua
moral
moral Turing Test (moTT)


mo
moral module
nature
nurture
dilemma
moral matrix (Haidt, 2012)
innate morality
hormones
mirror.ns
empathy
acquired morality
stories
MRFs
template
Story
("doch dichterisch wohnet Android auf dieser Erde")


stories
MRFs
templates
Morally Relevant Features (MRFs)


Templates


stories
MRFs
template
solving the dilemma
parse
match
act
Do not try to hit the ball, hit the ball...


1st principle: Experience induces new MRFs, templates and associates them to actions.
2nd principle: Time/entropy/dreams and new experience can modify such representations.

CAMTCHA


Man’s morality is a result of an inductive constructionist process. Input into the process are moral dilemmata or their storylike representations, its output are general patterns allowing to classify as moral or immoral even the dilemmas which were not represented in the initial training corpus. Moral inference process can be simulated by machine learning algorithms and can be based upon detection and extraction of morally relevant features. Supervised or semisupervised approaches should be used by those aiming to simulate parent -> child or teacher -> student information transfer processes in artificial agents. Preexisting models of inference e.g. the grammar inference models in the domain of computational linguistics can be exploited to build a moral induction model. Historical data, mythology or folklore could serve as a basis of the training corpus which could be subsequently significantly extended by a crowdsourcing method exploiting the webbased « Completely Automated Moral Turing test to tell Computers and Humans Apart ».

c.f. Hromada 2011 (Aarhus), 2012 (Birmingham), http://wizzion.com/iacap13/

Use a spacebar or arrow keys to navigate