Oscillatory model of attention-guided object selection and novelty detection

作者: Roman M Borisyuk , Yakov B Kazanovich

DOI: 10.1016/J.NEUNET.2004.03.005

关键词: Novelty detectionArtificial neural networkObject (computer science)Visual perceptionComputer scienceRepresentation (mathematics)Artificial intelligenceFeature extractionObject detectionComputer vision

摘要: We develop a new oscillatory model that combines consecutive selection of objects and discrimination between familiar objects. The works with visual information fulfils the following operations: (1) separation different according to their spatial connectivity; (2) located in field into attention focus; (3) extraction features; (4) representation working memory; (5) novelty detection functioning is based on two main principles: synchronization oscillators through phase-locking resonant increase amplitudes if they work in-phase other oscillators. results computer simulation are described for stimuli representing printed words.

参考文章(102)
Roger Cans, Jacques-Yves Cousteau (1910-97) Nature. ,vol. 388, pp. 334- 334 ,(1997) , 10.1038/40994
B. Hutcheon, R. M. Miura, E. Puil, Models of subthreshold membrane resonance in neocortical neurons Journal of Neurophysiology. ,vol. 76, pp. 698- 714 ,(1996) , 10.1152/JN.1996.76.2.698
V. I. Kryukov, An attention model based on the principle of dominanta Neurocomputers and Attention I. Neurobiology, Synchronization and Chaos. ,(1991)
Finger Wr, Closer review of condom breakage leading to more reliable product. IEEE Network. ,vol. 12, pp. 1- 15 ,(1991)
Robert T. Knight, Tsutomu Nakada, A Review of EEG and Blood Flow Data Reviews in The Neurosciences. ,vol. 9, pp. 57- 70 ,(1998) , 10.1515/REVNEURO.1998.9.1.57
O. S. Vinogradova, E. N. Sokolov, Neuronal mechanisms of the orienting reflex ,(1975)
Arun V. Holden, V. I. Kri︠u︡kov, Neurocomputers and Attention ,(1992)
B. Hutcheon, R. M. Miura, E. Puil, Subthreshold membrane resonance in neocortical neurons Journal of Neurophysiology. ,vol. 76, pp. 683- 697 ,(1996) , 10.1152/JN.1996.76.2.683