Characterizing an Analogical Concept Memory for Architectures Implementing the Common Model of Cognition
Architectures that implement the Common Model of Cognition - Soar, ACT-R, and Sigma - have a prominent place in research on cognitive modeling as well as on designing complex intelligent agents. In this paper, we explore how computational models of analogical processing can be brought into these arc...
Saved in:
Main Authors | , , , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
02.06.2020
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Architectures that implement the Common Model of Cognition - Soar, ACT-R, and
Sigma - have a prominent place in research on cognitive modeling as well as on
designing complex intelligent agents. In this paper, we explore how
computational models of analogical processing can be brought into these
architectures to enable concept acquisition from examples obtained
interactively. We propose a new analogical concept memory for Soar that
augments its current system of declarative long-term memories. We frame the
problem of concept learning as embedded within the larger context of
interactive task learning (ITL) and embodied language processing (ELP). We
demonstrate that the analogical learning methods implemented in the proposed
memory can quickly learn a diverse types of novel concepts that are useful not
only in recognition of a concept in the environment but also in action
selection. Our approach has been instantiated in an implemented cognitive
system \textsc{Aileen} and evaluated on a simulated robotic domain. |
---|---|
AbstractList | Architectures that implement the Common Model of Cognition - Soar, ACT-R, and
Sigma - have a prominent place in research on cognitive modeling as well as on
designing complex intelligent agents. In this paper, we explore how
computational models of analogical processing can be brought into these
architectures to enable concept acquisition from examples obtained
interactively. We propose a new analogical concept memory for Soar that
augments its current system of declarative long-term memories. We frame the
problem of concept learning as embedded within the larger context of
interactive task learning (ITL) and embodied language processing (ELP). We
demonstrate that the analogical learning methods implemented in the proposed
memory can quickly learn a diverse types of novel concepts that are useful not
only in recognition of a concept in the environment but also in action
selection. Our approach has been instantiated in an implemented cognitive
system \textsc{Aileen} and evaluated on a simulated robotic domain. |
Author | Mohan, Shiwali Maxwell, John Shreve, Matthew Klenk, Matt Ang, Aaron Evans, Kent |
Author_xml | – sequence: 1 givenname: Shiwali surname: Mohan fullname: Mohan, Shiwali – sequence: 2 givenname: Matt surname: Klenk fullname: Klenk, Matt – sequence: 3 givenname: Matthew surname: Shreve fullname: Shreve, Matthew – sequence: 4 givenname: Kent surname: Evans fullname: Evans, Kent – sequence: 5 givenname: Aaron surname: Ang fullname: Ang, Aaron – sequence: 6 givenname: John surname: Maxwell fullname: Maxwell, John |
BackLink | https://doi.org/10.48550/arXiv.2006.01962$$DView paper in arXiv |
BookMark | eNotj7tOwzAYRj3AAIUHYMIvkOBL7MRjFHGp1Iqle-Q6vxNLsR25BlGenrZ0-vQN50jnHt2EGAChJ0rKqhGCvOj0475LRogsCVWS3aGpm3TSJkNyvy6MWAfcBj3H0Rk94y4GA0vGW_AxHbGNCbfJTC6DyV8JDnjtlxk8hHxm8wQnwvsY8DYOMONoT38MLrsYHtCt1fMBHq-7Qru31133UWw-39dduym0rFkhiTASjFKUVmZvLGemNmqQSlW2MVRIXWlRSasaLqzUNd8TyQbeMCEUDJTyFXr-115S-yU5r9OxPyf3l2T-B-OKU_g |
ContentType | Journal Article |
Copyright | http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
Copyright_xml | – notice: http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
DBID | AKY GOX |
DOI | 10.48550/arxiv.2006.01962 |
DatabaseName | arXiv Computer Science arXiv.org |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: GOX name: arXiv.org url: http://arxiv.org/find sourceTypes: Open Access Repository |
DeliveryMethod | fulltext_linktorsrc |
ExternalDocumentID | 2006_01962 |
GroupedDBID | AKY GOX |
ID | FETCH-LOGICAL-a672-605c6ec99114cbcf32c7c9d6994f8c156a4a546f9835f6a73b062d382559ed113 |
IEDL.DBID | GOX |
IngestDate | Mon Jan 08 05:49:50 EST 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-a672-605c6ec99114cbcf32c7c9d6994f8c156a4a546f9835f6a73b062d382559ed113 |
OpenAccessLink | https://arxiv.org/abs/2006.01962 |
ParticipantIDs | arxiv_primary_2006_01962 |
PublicationCentury | 2000 |
PublicationDate | 2020-06-02 |
PublicationDateYYYYMMDD | 2020-06-02 |
PublicationDate_xml | – month: 06 year: 2020 text: 2020-06-02 day: 02 |
PublicationDecade | 2020 |
PublicationYear | 2020 |
Score | 1.7749473 |
SecondaryResourceType | preprint |
Snippet | Architectures that implement the Common Model of Cognition - Soar, ACT-R, and
Sigma - have a prominent place in research on cognitive modeling as well as on... |
SourceID | arxiv |
SourceType | Open Access Repository |
SubjectTerms | Computer Science - Artificial Intelligence Computer Science - Human-Computer Interaction Computer Science - Robotics Computer Science - Symbolic Computation |
Title | Characterizing an Analogical Concept Memory for Architectures Implementing the Common Model of Cognition |
URI | https://arxiv.org/abs/2006.01962 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwdV1LSwMxEA61Jy-iqNQnOXgN7ua5OZbFWoTqpcLeSpJNUJBdaauov95JUrUXj3ldJkPmm8nMNwhdtZwa5TwjVrSS8IozUpW-IMqDRjEdhBGxOHl2L6eP_K4RzQDhn1oYs_x4fs_8wHZ1nf8KQEngkd2hNKZs3T40-XMyUXFt9v_tA4yZpraMxGQf7W3QHR7n6zhAA98doqf6lxT5CwwFNh2OVCD5zcF1rhvEs5jy-okBQ-LxVnB_hRN_b0rqgbMA13Cs6eg7HLuYveA-wDhlAPXdEZpPbub1lGwaHBAjFSXgSTjpHSC0kjvrAqNOOd1KrXmoHDhWhhvBZdCAkoI0itlC0pZV0QvwbVmyYzTs-s6PEC4YF87ayldacCWoBksug_JMe26tNydolMSyeM0cFrH7pFwkiZ3-v3SGdml0L2PQgZ6j4Xr55i_ABq_tZbqIb8ARh24 |
link.rule.ids | 228,230,786,891 |
linkProvider | Cornell University |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Characterizing+an+Analogical+Concept+Memory+for+Architectures+Implementing+the+Common+Model+of+Cognition&rft.au=Mohan%2C+Shiwali&rft.au=Klenk%2C+Matt&rft.au=Shreve%2C+Matthew&rft.au=Evans%2C+Kent&rft.date=2020-06-02&rft_id=info:doi/10.48550%2Farxiv.2006.01962&rft.externalDocID=2006_01962 |