Abstract
It is a widely held view in contemporary computational neuroscience that the brain responds to sensory input by producing sparse distributed representations. In this paper we investigate a brain-inspired spatial pooling algorithm that produces such sparse distributed representations by modelling the formation of proximal dendrites associated with neocortical minicolumns. In this approach, distributed representations are formed out of a competitive process of inter-column inhibition and subsequent learning. Specifically, we evaluate the performance of a recently proposed binary spatial pooling algorithm on a well-known benchmark of greyscale natural images. Our main contribution is to augment the algorithm to handle greyscale images, and to produce better quality encodings of binary images. We also show that the augmented algorithm produces superior population and lifetime kurtosis measures in comparison to a number of other well-known coding schemes.
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 subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Chikkerur, S., Serre, T., Tan, C., Poggio, T.: What and where: A Bayesian inference theory of attention. Vision Research 50(22), 2233–2247 (2010)
George, D., Hawkins, J.: A hierarchical Bayesian model of invariant pattern recognition in the visual cortex. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN 2005), pp. 1812–1817 (2005)
Hawkins, J., Blakeslee, S.: On intelligence. Henry Holt, New York (2004)
Hyvärinen, A., Karhunen, J., Oja, E.: Independent Components Analysis. John Wiley and Sons, Inc., New York (2001)
Kohonen, T.: Self-organization and associative memory. Springer, Berlin (1989)
Lee, T.S., Mumford, D.: Hierarchical Bayesian inference in visual cortex. Journal of the Optical Society of America A 20(7), 1434–1448 (2003)
Mountcastle, V.B.: Introduction to the special issue on computation in cortical columns. Cerebral Cortex 13(1), 2–4 (2003)
Numenta Inc.: Hierarchical temporal memory including HTM cortical learning algorithms. Tech. rep., Numenta, Inc, Palto Alto (2010), http://www.numenta.com/htm-overview/education/HTM_CorticalLearningAlgorithms.pdf
Olshausen, B.A.: Sparse codes and spikes. In: Rao, R.P.N., Olshausen, B.A., Lewicki, M.S. (eds.) Probabilistic Models of the Brain: Perception and Neural Function, pp. 257–272. MIT Press, Cambridge (2002)
Stuart, G., Spruston, N., Häusser, M.: Dendrites. OUP, New York (2008)
Willmore, B., Tolhurst, D.J.: Characterizing the sparseness of neural codes. Network: Computational Neural Systems 12, 255–270 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Thornton, J., Srbic, A., Main, L., Chitsaz, M. (2011). Augmented Spatial Pooling. In: Wang, D., Reynolds, M. (eds) AI 2011: Advances in Artificial Intelligence. AI 2011. Lecture Notes in Computer Science(), vol 7106. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25832-9_27
Download citation
DOI: https://doi.org/10.1007/978-3-642-25832-9_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25831-2
Online ISBN: 978-3-642-25832-9
eBook Packages: Computer ScienceComputer Science (R0)