Concept Extrapolation: A Conceptual Primer

06/19/2023
by   Matija Franklin, et al.
0

This article is a primer on concept extrapolation - the ability to take a concept, a feature, or a goal that is defined in one context and extrapolate it safely to a more general context. Concept extrapolation aims to solve model splintering - a ubiquitous occurrence wherein the features or concepts shift as the world changes over time. Through discussing value splintering and value extrapolation the article argues that concept extrapolation is necessary for Artificial Intelligence alignment.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/26/2020

The Evolution of Concept-Acquisition based on Developmental Psychology

A conceptual system with rich connotation is key to improving the perfor...
research
04/09/2019

Mixing syntagmatic and paradigmatic information for concept detection

In the last decades, philosophers have begun using empirical data for co...
research
11/12/2022

Explainable Artificial Intelligence in Construction: The Content, Context, Process, Outcome Evaluation Framework

Explainable artificial intelligence is an emerging and evolving concept....
research
10/15/2019

How a minimal learning agent can infer the existence of unobserved variables in a complex environment

According to a mainstream position in contemporary cognitive science and...
research
11/05/2021

Feature Concepts for Data Federative Innovations

A feature concept, the essence of the data-federative innovation process...
research
01/30/2022

Existence and perception as the basis of AGI (Artificial General Intelligence)

As is known, AGI (Artificial General Intelligence), unlike AI, should op...
research
01/25/2016

Emerging Dimension Weights in a Conceptual Spaces Model of Concept Combination

We investigate the generation of new concepts from combinations of prope...

Please sign up or login with your details

Forgot password? Click here to reset