Atention-driven Perceptual Classification and Reasoning

• One of the central challenges for embodied and situated agents with limited memory and processing resources is how to process and react to a large amount of information that they receive continuously through their sensors. Secondly, a model of infor- mation fusion is also required: how perceptual and linguistic/conceptual information interact and drive their reasoning. We present a computational model for perceptual classification in probabilistic Type Theory with Records (TTR), a formal meaning representation layer for such agents. The model is based on the cognitive notion of attention.

Subject headings

SAMHÄLLSVETENSKAP  -- Psykologi -- Psykologi (hsv//swe)

SOCIAL SCIENCES  -- Psychology -- Psychology (hsv//eng)

NATURVETENSKAP  -- Data- och informationsvetenskap -- Språkteknologi (hsv//swe)

NATURAL SCIENCES  -- Computer and Information Sciences -- Language Technology (hsv//eng)

HUMANIORA  -- Språk och litteratur -- Jämförande språkvetenskap och allmän lingvistik (hsv//swe)

HUMANITIES  -- Languages and Literature -- General Language Studies and Linguistics (hsv//eng)

Keyword

type theory with records

ttr

classification

perception

interaction

priming

attention

Bayesian reasoning

embodied dialogue agents

Publication and Content Type

ref (subject category)

kon (subject category)