Abstract
The Continuum Neural Field Theory implements competition within topologically organized neural networks with lateral inhibitory connections. However, due to the polynomial complexity of matrix-based implementations, updating dense representations of the activity becomes computationally intractable when an adaptive resolution or an arbitrary number of input dimensions is required. This paper proposes an alternative to self-organizing maps with a sparse implementation based on Gaussian mixture models, promoting a trade-off in redundancy for higher computational efficiency and alleviating constraints on the underlying substrate.
This version reproduces the emergent attentional properties of the original equations, by directly applying them within a continuous approximation of a high dimensional neural field. The model is compatible with preprocessed sensory flows but can also be interfaced with artificial systems. This is particularly important for sensorimotor systems, where decisions and motor actions must be taken and updated in real-time. Preliminary tests are performed on a reactive color tracking application, using spatially distributed color features.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Alahakoon, D., Halgamuge, S.K., Srinivasan, B.: Dynamic self-organizing maps with controlled growth for knowledge discovery. IEEE Trans. Neural Netw. 11(3), 601–614 (2000)
Amari, S.-I.: Dynamics of pattern formation in lateral-inhibition type neural fields. Biol. Cybern. 27(2), 77–87 (1977)
Barandiaran, X.E., Di Paolo, E., Rohde, M.: Defining agency: Individuality, normativity, asymmetry, and spatio-temporality in action. Adapt. Behav. 17(5), 367–386 (2009)
Bellman, R.: Adaptive Control Processes: A Guided Tour. Princeton University Press, Princeton (1961)
Bickhard, M.H., Christensen, W.D.: Process dynamics of normative function. Monist 85(1), 3–28 (2002)
Bosking, W.H., Zhang, Y., Schofield, B., Fitzpatrick, D.: Orientation selectivity and the arrangement of horizontal connections in tree shrew striate cortex. J. Neurosci. 17(6), 2112–2127 (1997)
Brodmann, K.: Brodmann’s ‘Localisation in the Cerebral Cortex’. Smith-Gordon, London (1909/1994)
Burnod, Y.: An Adaptive Neural Network: The Cerebral Cortex. Masson, Paris (1989)
Castellanos Sánchez, C., Girau, B.: Dynamic pursuit with a bio-inspired neural model. In: Advanced Concepts for Intelligent Vision Systems—ACIVS 2005. Lecture Notes in Computer Science, vol. 3708, pp. 284–291 (2005)
Chevallier, S., Tarroux, P.: Visual focus with spiking neurons. In: European Symposium on Artificial Networks—Advances in Computational Intelligence and Learning (ESANN’2008), Bruges, April, pp. 23–25 (2008)
Childs, J., Lu, C.-C., Potter, J.: A fast, space-efficient algorithm for the approximation of images by an optimal sum of Gaussians. In: Graphics Interface, pp. 153–162 (2000)
CIE (Commission Internationale d’Eclairage): Colorimetry, 3rd edn. publication 15. Technical report, CIE Central Bureau, Vienna (2004)
Denève, S., Duhamel, J.-R., Pouget, A.: Optimal sensorimotor integration in recurrent cortical networks: A neural implementation of Kalman filters. J. Neurosci. 27(21), 5744–5756 (2007)
Díaz, J., Ros, E., Mota, S., Botella, G., Cañas, A., Sabatini, S.: Optical flow for cars overtaking monitor: the rear mirror blind spot problem. Technical report, Ecovision (European research project) (2003)
Goshtasby, A., O’Neill, W.D.: Curve fitting by a sum of Gaussians. CVGIP, Graph. Models Image Process. 56(4), 281–288 (1994)
Hubel, D.N., Wiesel, T.H.: Receptive fields, binocular interaction, and functional architecture in the cat’s visual cortex. J. Physiol. 160, 106–54 (1962)
Husbands, P., Smith, T., Jakobi, N., O’Shea, M.: Better living through chemistry: Evolving gasnets for robot control. Connect. Sci. 10(3–4), 185–210 (1998)
Kandel, E.R., Schwartz, J.H., Jessell, T.M.: Principles of Neural Science. McGraw-Hill, New York (2000)
Kohonen, T.: Self-organizing Maps. Springer, Berlin (1995)
Lathauwer, L.D., Moor, B.D., Vandewalle, J.: A multilinear singular value decomposition. SIAM J. Matrix Anal. Appl. 21(4), 1253–1278 (2000)
Ménard, O., Frezza-Buet, H.: Model of multi-modal cortical processing: coherent learning in self-organizing modules. Neural Netw. 18(5–6), 646–55 (2005)
Mountcastle, V.B.: Modality and topographic properties of single neurons of cat’s somatic sensory cortex. J. Neurophysiol. 20(4), 408–434 (1957)
Quinton, J.-C.: Exploring and optimizing dynamic neural fields parameters using genetic algorithms. In: Proceedings of IEEE World Congress on Computational Intelligence (IJCNN’2010), Barcelona, Spain, 2010
Quinton, J.-C., Buisson, J.-C.: Multilevel anticipative interactions for goal oriented behaviors. In: Proceedings of EpiRob’08—International Conference on Epigenetic Robotics, Brighton, UK, pp. 103–110 (2008). Lund University Cognitive Studies
Quinton, J.-C., Girau, B.: A sparse implementation of dynamic competition in continuous neural fields. In: Brain Inspired Cognitive Systems (BICS’2010), Madrid, 2010
Rodieck, R.W.: Quantitative analysis of cat retinal ganglion cell response to visual stimuli. Vis. Res. 5(11), 583–601 (1965)
Rougier, N., Boniface, Y.: Dynamic self-organising map. Neurocomputing 74(11), 1840–1847 (2010)
Rougier, N.P., Vitay, J.: Emergence of attention within a neural population. Neural Netw. 19(5), 573–581 (2006). doi:10.1016/j.neunet.2005.04.004
Taylor, J.G.: Neural bubble dynamics in two dimensions: Foundations. Biol. Cybern. 80, 5167–5174 (1999)
Tewarson, R.P.: Sparse Matrices. Academic Press, San Diego (1973)
Torres-Huitzil, C., Girau, B., Castellanos Sánchez, C.: On-chip visual perception of motion: a bio-inspired connectionist model on FPGA. Neural Netw. 18, 557–565 (2005)
Wennekers, T.: Separation of spatio-temporal receptive fields into sums of Gaussian components. J. Comput. Neurosci. 16(1), 27–38 (2004)
Wilson, H.R., Cowan, J.D.: A mathematical theory of the functional dynamics of cortical and thalamic nervous tissue. Kybernetic 13, 55–80 (1973)
Xu, W., Duchateau, J., Demuynck, K., Dologlou, I.: A new approach to merging Gaussian densities in large vocabulary continuous speech recognition. In: IEEE Benelux Signal Processing Symposium, pp. 231–234 (1998)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Science+Business Media, LLC
About this paper
Cite this paper
Quinton, JC., Girau, B., Lefort, M. (2011). Competition in High Dimensional Spaces Using a Sparse Approximation of Neural Fields. In: Hernández, C., et al. From Brains to Systems. Advances in Experimental Medicine and Biology, vol 718. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-0164-3_11
Download citation
DOI: https://doi.org/10.1007/978-1-4614-0164-3_11
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4614-0163-6
Online ISBN: 978-1-4614-0164-3
eBook Packages: Biomedical and Life SciencesBiomedical and Life Sciences (R0)