Companion cognitive systems: Design goals and lessons learned so far

Kenneth D Forbus; Matthew Klenk; Thomas R Hinrichs

doi:10.1109/MIS.2009.71

Companion cognitive systems: Design goals and lessons learned so far

Kenneth D Forbus, Matthew Klenk, Thomas R Hinrichs

Computer Science

Research output: Contribution to journal › Article › peer-review

35 Scopus citations

Abstract

The Companion cognitive architecture supports experiments in achieving human-level intelligence. The seven key features of cognitive architecture include analogical processing, extensive conceptual knowledge, flexible reasoning, and coarse-grained distributed implementation, broad learning at multiple levels, continuous operation, and natural interaction. The model for analogical matching is the Structure-Mapping Engine (SME) that computes mappings using algorithm, operating in polynomial time. The model for similarity-based retrieval is many are called/few are chosen (MAC/FAC) that takes as input a probe and a case library. Another design goal for Companions is to emulate the parallelism that's evident in human behavior. Companions are implemented as distributed systems that allocate individual nodes of a cluster computer to semi-independent, asynchronous processes (agents). Agents communicate internally using the Knowledge Query and Manipulation Language (KQML) with callbacks to support asynchronous queries and subscriptions to events.

Original language	English (US)
Pages (from-to)	36-46
Number of pages	11
Journal	IEEE Intelligent Systems
Volume	24
Issue number	4
DOIs	https://doi.org/10.1109/MIS.2009.71
State	Published - 2009

ASJC Scopus subject areas

Computer Networks and Communications
Artificial Intelligence

Access to Document

10.1109/MIS.2009.71

Cite this

@article{4b4cea217d45444781947e70d6884312,

title = "Companion cognitive systems: Design goals and lessons learned so far",

abstract = "The Companion cognitive architecture supports experiments in achieving human-level intelligence. The seven key features of cognitive architecture include analogical processing, extensive conceptual knowledge, flexible reasoning, and coarse-grained distributed implementation, broad learning at multiple levels, continuous operation, and natural interaction. The model for analogical matching is the Structure-Mapping Engine (SME) that computes mappings using algorithm, operating in polynomial time. The model for similarity-based retrieval is many are called/few are chosen (MAC/FAC) that takes as input a probe and a case library. Another design goal for Companions is to emulate the parallelism that's evident in human behavior. Companions are implemented as distributed systems that allocate individual nodes of a cluster computer to semi-independent, asynchronous processes (agents). Agents communicate internally using the Knowledge Query and Manipulation Language (KQML) with callbacks to support asynchronous queries and subscriptions to events.",

author = "Forbus, {Kenneth D} and Matthew Klenk and Hinrichs, {Thomas R}",

note = "Funding Information: This work has been supported by DARPA under an Information Processing Techniques Office seedling and the Transfer Learning Program, and by the US Office of Naval Research under the Intelligent Systems and Cognitive Science Programs.",

year = "2009",

doi = "10.1109/MIS.2009.71",

language = "English (US)",

volume = "24",

pages = "36--46",

journal = "IEEE Expert",

issn = "1541-1672",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "4",

}

TY - JOUR

T1 - Companion cognitive systems

T2 - Design goals and lessons learned so far

AU - Forbus, Kenneth D

AU - Klenk, Matthew

AU - Hinrichs, Thomas R

N1 - Funding Information: This work has been supported by DARPA under an Information Processing Techniques Office seedling and the Transfer Learning Program, and by the US Office of Naval Research under the Intelligent Systems and Cognitive Science Programs.

PY - 2009

Y1 - 2009

N2 - The Companion cognitive architecture supports experiments in achieving human-level intelligence. The seven key features of cognitive architecture include analogical processing, extensive conceptual knowledge, flexible reasoning, and coarse-grained distributed implementation, broad learning at multiple levels, continuous operation, and natural interaction. The model for analogical matching is the Structure-Mapping Engine (SME) that computes mappings using algorithm, operating in polynomial time. The model for similarity-based retrieval is many are called/few are chosen (MAC/FAC) that takes as input a probe and a case library. Another design goal for Companions is to emulate the parallelism that's evident in human behavior. Companions are implemented as distributed systems that allocate individual nodes of a cluster computer to semi-independent, asynchronous processes (agents). Agents communicate internally using the Knowledge Query and Manipulation Language (KQML) with callbacks to support asynchronous queries and subscriptions to events.

AB - The Companion cognitive architecture supports experiments in achieving human-level intelligence. The seven key features of cognitive architecture include analogical processing, extensive conceptual knowledge, flexible reasoning, and coarse-grained distributed implementation, broad learning at multiple levels, continuous operation, and natural interaction. The model for analogical matching is the Structure-Mapping Engine (SME) that computes mappings using algorithm, operating in polynomial time. The model for similarity-based retrieval is many are called/few are chosen (MAC/FAC) that takes as input a probe and a case library. Another design goal for Companions is to emulate the parallelism that's evident in human behavior. Companions are implemented as distributed systems that allocate individual nodes of a cluster computer to semi-independent, asynchronous processes (agents). Agents communicate internally using the Knowledge Query and Manipulation Language (KQML) with callbacks to support asynchronous queries and subscriptions to events.

UR - http://www.scopus.com/inward/record.url?scp=70350575709&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70350575709&partnerID=8YFLogxK

U2 - 10.1109/MIS.2009.71

DO - 10.1109/MIS.2009.71

M3 - Article

AN - SCOPUS:70350575709

SN - 1541-1672

VL - 24

SP - 36

EP - 46

JO - IEEE Expert

JF - IEEE Expert

IS - 4

ER -

Companion cognitive systems: Design goals and lessons learned so far

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this