Analogy and qualitative representations in the companion cognitive architecture

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

The Companion cognitive architecture is aimed at reaching human-level AI by creating software social organisms - systems that interact with people using natural modalities, working and learning over extended periods of time as collaborators rather than tools. Our two central hypotheses about how to achieve this are (1) analogical reasoning and learning are central to cognition, and (2) qualitative representations provide a level of description that facilitates reasoning, learning, and communication. This article discusses the evidence we have gathered supporting these hypotheses from our experiments with the Companion architecture. Although we are far from our ultimate goals, these experiments provide strong evidence for the utility of analogy and qualitative representation across a range of tasks. We also discuss three lessons learned and highlight three important open problems for cognitive systems research more broadly.

Original languageEnglish (US)
Pages (from-to)34-42
Number of pages9
JournalAI Magazine
Volume38
Issue number4
StatePublished - Dec 1 2017

Fingerprint

Cognitive systems
Experiments
Communication

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

@article{72afa16f117442b5a1e0ea2786718dbc,
title = "Analogy and qualitative representations in the companion cognitive architecture",
abstract = "The Companion cognitive architecture is aimed at reaching human-level AI by creating software social organisms - systems that interact with people using natural modalities, working and learning over extended periods of time as collaborators rather than tools. Our two central hypotheses about how to achieve this are (1) analogical reasoning and learning are central to cognition, and (2) qualitative representations provide a level of description that facilitates reasoning, learning, and communication. This article discusses the evidence we have gathered supporting these hypotheses from our experiments with the Companion architecture. Although we are far from our ultimate goals, these experiments provide strong evidence for the utility of analogy and qualitative representation across a range of tasks. We also discuss three lessons learned and highlight three important open problems for cognitive systems research more broadly.",
author = "Forbus, {Kenneth D} and Hinrichs, {Thomas R}",
year = "2017",
month = "12",
day = "1",
language = "English (US)",
volume = "38",
pages = "34--42",
journal = "AI Magazine",
issn = "0738-4602",
publisher = "AI Access Foundation",
number = "4",

}

Analogy and qualitative representations in the companion cognitive architecture. / Forbus, Kenneth D; Hinrichs, Thomas R.

In: AI Magazine, Vol. 38, No. 4, 01.12.2017, p. 34-42.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Analogy and qualitative representations in the companion cognitive architecture

AU - Forbus, Kenneth D

AU - Hinrichs, Thomas R

PY - 2017/12/1

Y1 - 2017/12/1

N2 - The Companion cognitive architecture is aimed at reaching human-level AI by creating software social organisms - systems that interact with people using natural modalities, working and learning over extended periods of time as collaborators rather than tools. Our two central hypotheses about how to achieve this are (1) analogical reasoning and learning are central to cognition, and (2) qualitative representations provide a level of description that facilitates reasoning, learning, and communication. This article discusses the evidence we have gathered supporting these hypotheses from our experiments with the Companion architecture. Although we are far from our ultimate goals, these experiments provide strong evidence for the utility of analogy and qualitative representation across a range of tasks. We also discuss three lessons learned and highlight three important open problems for cognitive systems research more broadly.

AB - The Companion cognitive architecture is aimed at reaching human-level AI by creating software social organisms - systems that interact with people using natural modalities, working and learning over extended periods of time as collaborators rather than tools. Our two central hypotheses about how to achieve this are (1) analogical reasoning and learning are central to cognition, and (2) qualitative representations provide a level of description that facilitates reasoning, learning, and communication. This article discusses the evidence we have gathered supporting these hypotheses from our experiments with the Companion architecture. Although we are far from our ultimate goals, these experiments provide strong evidence for the utility of analogy and qualitative representation across a range of tasks. We also discuss three lessons learned and highlight three important open problems for cognitive systems research more broadly.

UR - http://www.scopus.com/inward/record.url?scp=85040841500&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040841500&partnerID=8YFLogxK

M3 - Article

VL - 38

SP - 34

EP - 42

JO - AI Magazine

JF - AI Magazine

SN - 0738-4602

IS - 4

ER -