Designing an active visual system, able to autonomously learn its behavior, implies to make the learning controller independent of an external signal (e.g. the error between the actual and the desired vergence angle) or of perceptual decisions about disparity (e.g. from the response of a previously trained network). The proposed approach is based on a direct use of a computational substrate of modeled V1 complex cells that provide a distributed representation of binocular disparity information. The design strategies of the cortical-like architecture, including uniform coverage in feature space and divisive normalization mechanisms, allow the global energy of the population to effectively mediate the learning process towards the proper motor control. Since the learning controller is based on an intrinsic representation of the visual signal, it comes to overlap and coincide with the system that is learning the behaviour, thus closing at an inner cycle the perception-action loop necessary for learning. Experimental tests proved that the control architecture is both able to learn an effective vergence behavior, and to exploit it to fixate static and moving visual targets. © 2012 Published by Elsevier B.V.
How a population-based representation of binocular visual signal can intrinsically mediate autonomous learning of vergence control / Gibaldi, A.; Canessa, A.; Chessa, M.; Solari, F.; Sabatini, S. P.. - In: PROCEDIA COMPUTER SCIENCE. - ISSN 1877-0509. - 13:(2012), pp. 212-221. (Intervento presentato al convegno 3rd International Neural Network Society Winter Conference, INNS-WC 2012 tenutosi a Bangkok, tha nel OCT 03-05, 2012) [10.1016/j.procs.2012.09.131].
How a population-based representation of binocular visual signal can intrinsically mediate autonomous learning of vergence control
Gibaldi A.;Canessa A.;
2012
Abstract
Designing an active visual system, able to autonomously learn its behavior, implies to make the learning controller independent of an external signal (e.g. the error between the actual and the desired vergence angle) or of perceptual decisions about disparity (e.g. from the response of a previously trained network). The proposed approach is based on a direct use of a computational substrate of modeled V1 complex cells that provide a distributed representation of binocular disparity information. The design strategies of the cortical-like architecture, including uniform coverage in feature space and divisive normalization mechanisms, allow the global energy of the population to effectively mediate the learning process towards the proper motor control. Since the learning controller is based on an intrinsic representation of the visual signal, it comes to overlap and coincide with the system that is learning the behaviour, thus closing at an inner cycle the perception-action loop necessary for learning. Experimental tests proved that the control architecture is both able to learn an effective vergence behavior, and to exploit it to fixate static and moving visual targets. © 2012 Published by Elsevier B.V.File | Dimensione | Formato | |
---|---|---|---|
1-s2.0-S1877050912007387-main.pdf
Open access
Tipologia:
Versione pubblicata dall'editore
Dimensione
341.12 kB
Formato
Adobe PDF
|
341.12 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris