Pregled bibliografske jedinice broj: 552954
A competitive network for multi-object selection
A competitive network for multi-object selection // Proceedings of thw World Congress on Computational Intelligence
Barcelona: Institute of Electrical and Electronics Engineers (IEEE), 2010. str. 1-6 (poster, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 552954 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
A competitive network for multi-object selection
Autori
Domijan, Dražen
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of thw World Congress on Computational Intelligence
/ - Barcelona : Institute of Electrical and Electronics Engineers (IEEE), 2010, 1-6
ISBN
978-1-4244-6916-1
Skup
2010 World Congress on Computational Intelligence
Mjesto i datum
Barcelona, Španjolska, 18.07.2010. - 23.07.2010
Vrsta sudjelovanja
Poster
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Attention; Neural networks; Lateral inhibition; WTA
Sažetak
Psychophysical and neurophysiological investi-gations shows that visual system is able to simultaneously select and attend to multiple objects present in the visual scene. A neural network is proposed with the ability to select multiple objects simultaneously if they share the same level of saliency. The model is based on the segmentation network which labels all spatial locations occupied by the object with the same activity level. Computer simulations showed that the model can perform visual search task with parallel access to multiple instances of the same object. Visual search is implemented using dynamic routing circuit which achieves translation-invariant representation of selected objects. Attentional shifts are imple-mented using template matching between sensory and memory representation. If there is a mismatch between them, a global inhibition drives the whole network to search for a new pattern. The proposed network is able to select objects even when their visual representation is corrupted with Gaussian noise. The model’s behavior is consistent with the Boolean map theory of visual attention.
Izvorni jezik
Engleski
Znanstvena područja
Psihologija
POVEZANOST RADA
Projekti:
009-0362214-0818 - Neuronsko modeliranje i bihevioralno testiranje vidne percepcije i kognicije (Domijan, Dražen, MZOS ) ( CroRIS)
Ustanove:
Filozofski fakultet, Rijeka
Profili:
Dražen Domijan
(autor)