Temporal semantics: An Adaptive Resonance Theory approach

Author

Taylor, S.E. ; Bernard, M.L. ; Verzi, S.J. ; Morrow, J.D. ; Vineyard, C.M. ; Healy, M.J. ; Caudell, T.P.

Author_Institution

Sandia Nat. Labs., Albuquerque, NM, USA

fYear

2009

fDate

14-19 June 2009

Firstpage

3111

Lastpage

3117

Abstract

Encoding sensor observations across time is a critical component in the ability to model cognitive processes. All biological cognitive systems receive sensory stimuli as continuous streams of observed data over time. Therefore, the perceptual grounding of all biological cognitive processing is in temporal semantic encodings, where the particular grounding semantics are sensor modalities. We introduce a technique that encodes temporal semantic data as temporally integrated patterns stored in adaptive resonance theory (ART) modules.

Keywords

ART neural nets; adaptive codes; cognitive systems; temporal reasoning; ART; adaptive resonance theory approach; artificial neural architecture; biological cognitive system; sensor observation encoding; temporal semantics; temporally integrated pattern; Biological information theory; Biological neural networks; Biological system modeling; Biosensors; Encoding; Grounding; Neural networks; Resonance; Subspace constraints; Unsupervised learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2009. IJCNN 2009. International Joint Conference on

Conference_Location

Atlanta, GA

ISSN

1098-7576

Print_ISBN

978-1-4244-3548-7

Electronic_ISBN

1098-7576

Type

conf

DOI

10.1109/IJCNN.2009.5178925

Filename

5178925