Matches in SemOpenAlex for { <https://semopenalex.org/work/W2364268578> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W2364268578 abstract "We are working on a computational model of color perception and color naming, which can be seen as an instance of symbol grounding [4] in the domain of color, or as an attempt to provide an artificial intelligent agent with embodied concepts of color. This effort is part of a larger one in the field of intelligent autonomous agents [8, 5], and will provide a perceptual grounding for some of the symbolic representations in the SNAPS Knowledge Representation formalism [13], especially those referred to as sensory nodes [12]. The implemented model will allow an agent to name colors in its environment, point out examples of named colors in its environment, and learn new names for colors. Our research draws on work in the neurophysiology of color perception, particularly [3], in semantic universals for natural languages, particularly [1], and other work in AI and Cognitive Science. We discuss two areas of the model where learning is used: learning a non-linear mapping between two color spaces, and learning a relation between color coordinates and a set of symbolic color names. We have used a traditional error back-propagation learning algorithm for the first problem, and are considering several different learning paradigms for the second problem, ranging from traditional clustering techniques to an experimental space warp method. Using learning gives us a relatively easy way to determine a non-linear transformation of spaces in the first case, and increases the flexibility of the approach with respect to different application needs (and languages) in the second case. discuss the learning methods used or considered and the problems encountered. In general terms, our model has to explain (and reproduce) a signal-to-symbol transition, going from light entering a sensor to symbols representing the corresponding perceived color. To make our problem manageable, we make some simplifying assumptions. We are only concerned with single-point determination of color, thus disregarding spatial interactions in color perception. We only take context into account to the extent that it is necessary for this determination. We assume foveal cone photoreceptors as sensors, and we restrict the problem" @default.
- W2364268578 created "2016-06-24" @default.
- W2364268578 creator A5030334025 @default.
- W2364268578 creator A5057024532 @default.
- W2364268578 date "1993-01-01" @default.
- W2364268578 modified "2023-09-26" @default.
- W2364268578 title "Learning Symbolic Names for Perceived Colors" @default.
- W2364268578 cites W1537670585 @default.
- W2364268578 cites W1971179077 @default.
- W2364268578 cites W1974689608 @default.
- W2364268578 cites W1982954510 @default.
- W2364268578 cites W1991358523 @default.
- W2364268578 cites W2063240138 @default.
- W2364268578 cites W2115793726 @default.
- W2364268578 cites W2116531877 @default.
- W2364268578 cites W2124699749 @default.
- W2364268578 cites W2766736793 @default.
- W2364268578 hasPublicationYear "1993" @default.
- W2364268578 type Work @default.
- W2364268578 sameAs 2364268578 @default.
- W2364268578 citedByCount "3" @default.
- W2364268578 crossrefType "journal-article" @default.
- W2364268578 hasAuthorship W2364268578A5030334025 @default.
- W2364268578 hasAuthorship W2364268578A5057024532 @default.
- W2364268578 hasConcept C100609095 @default.
- W2364268578 hasConcept C115961682 @default.
- W2364268578 hasConcept C134400042 @default.
- W2364268578 hasConcept C154945302 @default.
- W2364268578 hasConcept C15744967 @default.
- W2364268578 hasConcept C169760540 @default.
- W2364268578 hasConcept C199360897 @default.
- W2364268578 hasConcept C26760741 @default.
- W2364268578 hasConcept C2961294 @default.
- W2364268578 hasConcept C41008148 @default.
- W2364268578 hasConceptScore W2364268578C100609095 @default.
- W2364268578 hasConceptScore W2364268578C115961682 @default.
- W2364268578 hasConceptScore W2364268578C134400042 @default.
- W2364268578 hasConceptScore W2364268578C154945302 @default.
- W2364268578 hasConceptScore W2364268578C15744967 @default.
- W2364268578 hasConceptScore W2364268578C169760540 @default.
- W2364268578 hasConceptScore W2364268578C199360897 @default.
- W2364268578 hasConceptScore W2364268578C26760741 @default.
- W2364268578 hasConceptScore W2364268578C2961294 @default.
- W2364268578 hasConceptScore W2364268578C41008148 @default.
- W2364268578 hasLocation W23642685781 @default.
- W2364268578 hasOpenAccess W2364268578 @default.
- W2364268578 hasPrimaryLocation W23642685781 @default.
- W2364268578 hasRelatedWork W101708207 @default.
- W2364268578 hasRelatedWork W122899419 @default.
- W2364268578 hasRelatedWork W1237306684 @default.
- W2364268578 hasRelatedWork W2067698844 @default.
- W2364268578 hasRelatedWork W2126296436 @default.
- W2364268578 hasRelatedWork W2158455240 @default.
- W2364268578 hasRelatedWork W2325295175 @default.
- W2364268578 hasRelatedWork W2590960023 @default.
- W2364268578 hasRelatedWork W2736019926 @default.
- W2364268578 hasRelatedWork W2750069989 @default.
- W2364268578 hasRelatedWork W2949559657 @default.
- W2364268578 hasRelatedWork W2962739176 @default.
- W2364268578 hasRelatedWork W2963104543 @default.
- W2364268578 hasRelatedWork W2963117534 @default.
- W2364268578 hasRelatedWork W2966698822 @default.
- W2364268578 hasRelatedWork W2969000870 @default.
- W2364268578 hasRelatedWork W2987068636 @default.
- W2364268578 hasRelatedWork W3023745006 @default.
- W2364268578 hasRelatedWork W3211003470 @default.
- W2364268578 hasRelatedWork W6601945 @default.
- W2364268578 isParatext "false" @default.
- W2364268578 isRetracted "false" @default.
- W2364268578 magId "2364268578" @default.
- W2364268578 workType "article" @default.