Abstract
We describe an associator neural network to localise a recognised object within the visual field. The idea extends the use of lateral connections within a single cortical area to their use between different areas. Previously, intra-area lateral connections have been implemented within V1 to endow the simple cells with biologically realistic orientation tuning curves as well as to generate complex cell properties. In this paper we extend the lateral connections to also span an area laterally connected to the simulated V1. Their training was done by the following procedure: every image on the input contained an artificially generated orange fruit at a particular location. This location was reflected – in a supervised manner – as a Gaussian on the area laterally connected to V1. Thus, the lateral weights are trained to associate the V1 representation of the image to the location of the orange. After training, we present an image with an orange of which we do not know its location. By the means of pattern completion a Gaussian hill of activation emerges on the correct location of the laterally connected area. Tests display a good performance with real oranges under diverse lighting and backgrounds. A further extension to include multi-modal input is discussed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
P. Dayan. Recurrent sampling models for the Helmholtz machine. Neur. Comp., 11:653–77, 2000.
S. Deneve, P.E. Latham, and A. Pouget. Reading population codes: a neural implementation of ideal observers. Nature Neurosci., 2(8):740–5, 1999.
D.J. Felleman and D.C. Van Essen. Distributed hierarchical processing in the primate cerebral cortex. Cerebral Cortex, 1:1–47, 1991.
P.O. Hoyer and A. Hyvärinen. Independent component analysis applied to feature extraction from colour and stereo images. Network: Comput. Neural Syst., 11(3):191–210, 2000.
A.K. Moschovakis, G.G. Gregoriou, and H.E. Savaki. Functional imaging of the primate superior colliculus during saccades to visual targets. Nature Neurosci., 4(10):1026–31, 2001.
F Pulvermüller. A brain perspective on language mechanisms: from discrete neuronal ensembles to serial order. Progress in Neurobiology, 67:85–111, 2002.
R.P.N. Rao and D.H. Ballard. Development of localized oriented receptive fields by learning a translation-invariant code for natural images. Network: Comput. Neural Syst., 9:219–37, 1998.
R.P.N. Rao, G.J. Zelinsky, M.M. Mayhoe, and D.H. Ballard. Eye movements in iconic visual search. Vis. Res., 42(11):1447–63, 2002.
G. Rizzolatti and G. Luppino. Cortical motor system. Neuron, 31:889–901, 2001.
J. Sirosh and R. Miikkulainen. Topographic receptive fields and patterned lateral interaction in a self-organizing model of the primary visual cortex. Neur. Comp., 9:577–94, 1997.
J. Sirosh, R. Miikkulainen, and Y. Choe, editors. Lateral Interactions in the Cortex: Structure and Function. Hypertext Book, http://www.cs.utexas.edu/users/nn/webpubs/htmlbook96, 1996.
J. Sullivan, A. Blake, M. Isard, and J. MacCormick. Bayesian object localisation in images. Int. J. Computer Vision, 44(2):111–35, 2001.
C. Weber. Self-organization of orientation maps, lateral connections, and dynamic receptive fields in the primary visual cortex. In G. Dorffner, H. Bischof, and K. Hornik, editors, Proceedings ICANN, pages 1147–52, 2001.
C. Weber and K. Obermayer. Emergent Neural Computational Architectures, chapter Emergence of modularity within one sheet of neurons: a model comparison, pages 53–76. Springer-Verlag Berlin Heidelberg, 2001.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Weber, C., Wermter, S. (2003). Object Localisation Using Laterally Connected “What” and “Where” Associator Networks. In: Kaynak, O., Alpaydin, E., Oja, E., Xu, L. (eds) Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003. ICANN ICONIP 2003 2003. Lecture Notes in Computer Science, vol 2714. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44989-2_97
Download citation
DOI: https://doi.org/10.1007/3-540-44989-2_97
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40408-8
Online ISBN: 978-3-540-44989-8
eBook Packages: Springer Book Archive