Artificial general segmentation

Daniel Hewlett, Paul R Cohen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

We argue that the ability to find meaningful chunks in sequential input is a core cognitive ability for artificial general intelligence, and that the Voting Experts algorithm, which searches for an information theoretic signature of chunks, provides a general implementation of this ability. In support of this claim, we demonstrate that VE successfully finds chunks in a wide variety of domains, solving such diverse tasks as word segmentation and morphology in multiple languages, visually recognizing letters in text, finding episodes in sequences of robot actions, and finding boundaries in the instruction of an AI student. We also discuss further desirable attributes of a general chunking algorithm, and show that VE possesses them.

Original languageEnglish (US)
Title of host publicationArtificial General Intelligence - Proceedings of the Third Conference on Artificial General Intelligence, AGI 2010
Pages31-36
Number of pages6
StatePublished - 2010
Event3rd Conference on Artificial General Intelligence, AGI 2010 - Lugano, Switzerland
Duration: Mar 5 2010Mar 8 2010

Other

Other3rd Conference on Artificial General Intelligence, AGI 2010
CountrySwitzerland
CityLugano
Period3/5/103/8/10

Fingerprint

Robots
Students

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Hewlett, D., & Cohen, P. R. (2010). Artificial general segmentation. In Artificial General Intelligence - Proceedings of the Third Conference on Artificial General Intelligence, AGI 2010 (pp. 31-36)

Artificial general segmentation. / Hewlett, Daniel; Cohen, Paul R.

Artificial General Intelligence - Proceedings of the Third Conference on Artificial General Intelligence, AGI 2010. 2010. p. 31-36.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hewlett, D & Cohen, PR 2010, Artificial general segmentation. in Artificial General Intelligence - Proceedings of the Third Conference on Artificial General Intelligence, AGI 2010. pp. 31-36, 3rd Conference on Artificial General Intelligence, AGI 2010, Lugano, Switzerland, 3/5/10.
Hewlett D, Cohen PR. Artificial general segmentation. In Artificial General Intelligence - Proceedings of the Third Conference on Artificial General Intelligence, AGI 2010. 2010. p. 31-36
Hewlett, Daniel ; Cohen, Paul R. / Artificial general segmentation. Artificial General Intelligence - Proceedings of the Third Conference on Artificial General Intelligence, AGI 2010. 2010. pp. 31-36
@inproceedings{6fbef1ff0efb4f279e0684ef714b1187,
title = "Artificial general segmentation",
abstract = "We argue that the ability to find meaningful chunks in sequential input is a core cognitive ability for artificial general intelligence, and that the Voting Experts algorithm, which searches for an information theoretic signature of chunks, provides a general implementation of this ability. In support of this claim, we demonstrate that VE successfully finds chunks in a wide variety of domains, solving such diverse tasks as word segmentation and morphology in multiple languages, visually recognizing letters in text, finding episodes in sequences of robot actions, and finding boundaries in the instruction of an AI student. We also discuss further desirable attributes of a general chunking algorithm, and show that VE possesses them.",
author = "Daniel Hewlett and Cohen, {Paul R}",
year = "2010",
language = "English (US)",
isbn = "9789078677369",
pages = "31--36",
booktitle = "Artificial General Intelligence - Proceedings of the Third Conference on Artificial General Intelligence, AGI 2010",

}

TY - GEN

T1 - Artificial general segmentation

AU - Hewlett, Daniel

AU - Cohen, Paul R

PY - 2010

Y1 - 2010

N2 - We argue that the ability to find meaningful chunks in sequential input is a core cognitive ability for artificial general intelligence, and that the Voting Experts algorithm, which searches for an information theoretic signature of chunks, provides a general implementation of this ability. In support of this claim, we demonstrate that VE successfully finds chunks in a wide variety of domains, solving such diverse tasks as word segmentation and morphology in multiple languages, visually recognizing letters in text, finding episodes in sequences of robot actions, and finding boundaries in the instruction of an AI student. We also discuss further desirable attributes of a general chunking algorithm, and show that VE possesses them.

AB - We argue that the ability to find meaningful chunks in sequential input is a core cognitive ability for artificial general intelligence, and that the Voting Experts algorithm, which searches for an information theoretic signature of chunks, provides a general implementation of this ability. In support of this claim, we demonstrate that VE successfully finds chunks in a wide variety of domains, solving such diverse tasks as word segmentation and morphology in multiple languages, visually recognizing letters in text, finding episodes in sequences of robot actions, and finding boundaries in the instruction of an AI student. We also discuss further desirable attributes of a general chunking algorithm, and show that VE possesses them.

UR - http://www.scopus.com/inward/record.url?scp=77954136464&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954136464&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9789078677369

SP - 31

EP - 36

BT - Artificial General Intelligence - Proceedings of the Third Conference on Artificial General Intelligence, AGI 2010

ER -