Skip navigation
Skip navigation

Symbol Statistics for Concept Formation in AI Agents

Chen, Jason Robert

Description

High level conceptual thought seems to be at the basis of the impressive human cognitive ability. Classical top-down (Logic based) and bottom-up (Connectionist) approaches to the problem have had limited success to date. We identify a small body of work that represents a different approach to AI. We call this work the Bottom Up Symbolic (BUS) approach and present a new BUS method to concept construction. The main novelty of our work is that we apply statistical methods in the concept...[Show more]

dc.contributor.authorChen, Jason Robert
dc.coverage.spatialMilan Italy
dc.date.accessioned2015-12-10T22:22:01Z
dc.date.createdSeptember 15-18 2009
dc.identifier.isbn9780769538013
dc.identifier.urihttp://hdl.handle.net/1885/52467
dc.description.abstractHigh level conceptual thought seems to be at the basis of the impressive human cognitive ability. Classical top-down (Logic based) and bottom-up (Connectionist) approaches to the problem have had limited success to date. We identify a small body of work that represents a different approach to AI. We call this work the Bottom Up Symbolic (BUS) approach and present a new BUS method to concept construction. The main novelty of our work is that we apply statistical methods in the concept construction process. Our findings here suggest that such methods are necessary since a symbolic description of the true agent-environment interaction dynamics is often hidden among a background of non-representative descriptions, especially if data from unconstrained real-world experiments is considered. We consider such data (from a mobile robot randomly roaming an office environment) and show how our method can correctly grow a set of true concepts from the data.
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE Inc)
dc.relation.ispartofseriesIEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology (IAT 2009)
dc.sourceProceedings of the IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology (IAT 2009)
dc.subjectKeywords: Category; Cognitive architectures; Concept formation; Construction process; Entailment; Human cognitive abilities; Interaction dynamics; Office environments; Real world experiment; Small bodies; Symbolic description; Topdown; Intelligent agents Bottom up AI; Category; Cognitive architecture; Concept formation; Entailment; Symbol statistics
dc.titleSymbol Statistics for Concept Formation in AI Agents
dc.typeConference paper
local.description.notesImported from ARIES
local.description.refereedYes
dc.date.issued2009
local.identifier.absfor080101 - Adaptive Agents and Intelligent Robotics
local.identifier.ariespublicationu4334215xPUB247
local.type.statusPublished Version
local.contributor.affiliationChen, Jason Robert, College of Engineering and Computer Science, ANU
local.description.embargo2037-12-31
local.bibliographicCitation.startpage249
local.bibliographicCitation.lastpage254
local.identifier.doi10.1109/WI-IAT.2009.157
dc.date.updated2016-02-24T10:59:25Z
local.identifier.scopusID2-s2.0-84863163127
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Chen_Symbol_Statistics_for_Concept_2009.pdf333.45 kBAdobe PDF    Request a copy


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator