Abstract
Although the basic sparse coding model has been quite successful at explaining the receptive fields of simple cells in V1, it ignores an important constrain: perception task. We put forward a novel sparse coding model, called task-oriented sparse coding (TOSC) model, combining the discriminability constrain supervised by classification task, besides the sparseness criteria. Simulation experiments are performed using real images including class of scene and class of building. The results show that TOSC can organize some significant receptive fields with distinct topological structure which will favor the classification task. Moreover, the coefficients of TOSC notablely improve the classification accuracy, from the 53.5% of pixel-based model to 86.7%, in the case of none distinct damage on the performance of reconstruction error and sparseness. TOSC model, complementing the feedback sparse coding model, is more consistent with biological mechanism, and shows good potential in the feature extraction for pattern classification.
This paper is supported by National Natural Science Foundation of China No. 60435010 and National Basic Research Priorities Programme No. 2003CB317004.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Olshausen, B.A., Field, D.J.: Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381, 131–133 (1996)
Vinje, W.E., Gallant, J.L.: Sparse coding and decorrelation in primary visual cortex during natural vision. Science 287, 1273–1276 (2000)
Vinje, W.E., Gallant, J.L.: Natural stimulation of the nonclassical receptive field increases information transmission efficiency in V1. Journal Neuronscience 22, 2904–2915 (2002)
Kac, M.: Microciruits in visual cortex. Current Opin Neuronbiol. 12, 418–425 (2002)
Douglas, R.J., Koch, C., Mahowald, M., Martin, K.A., Suarez, H.H.: Recurrent excitation in neocortical circuits. Science 269, 981–985 (1995)
Barlow, H.B.: Single units and sensation: a neuron doctrine for perceptual psychology? Perception 1, 371–394 (1972)
Mumford, D.: Neuronal architectures for pattern-theoretic problems. In: Koch, C., Davis, J.L. (eds.) Large scale neuronal theories of the brain, pp. 125–152. MIT Press, Cambridge (1997)
Friedman, J.H.: Exploratory projection pursuit. Journal of the American Statistical Association 82, 249–266 (1987)
Atick, J.J., Redlich, A.N.: Towards a theory of early visual processing. Neural Computation 2, 308–320 (1990)
Olshausen, B.A., Field, D.J.: Sparse coding with an overcomplete basis set: A strategy employed by V1? Vision Research 37, 3311–3325 (1997)
Olshausen, B.A., David, J.F.: Sparse coding of sensory inputs. Current Opinion in Neurobilogy 14, 481–487 (2004)
Levy, W.B., Baxter, R.A.: Energy efficient neural codes. Neural Computation 8, 531–543 (1996)
Atick, J.J., Redlich, A.N.: Convergent algorithm for sensory receptive field development. Neural Computation 5, 45–60 (1993)
Bell, A.J., Sejnowski, T.J.: The “Independent components” of natural scenes are edge filters. Vision Research 37, 3327–3338 (1997)
Gilbert, C.D., Wiesel, T.N.: Morphology and intracortical projections of functionally identified neurons in cat visual cortex. Nature 280, 120–125 (1979)
Miikkulainen, R., Sirosh, J.: Introduction: the emerging understanding of lateral interactions in the cortex. Lateral interaction in the cortex: structure and function. Electronic book ISBN 0-9647060-0-8
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, Q., Lin, D., Shi, Z. (2005). Task-Oriented Sparse Coding Model for Pattern Classification. In: Wang, L., Chen, K., Ong, Y.S. (eds) Advances in Natural Computation. ICNC 2005. Lecture Notes in Computer Science, vol 3610. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11539087_121
Download citation
DOI: https://doi.org/10.1007/11539087_121
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28323-2
Online ISBN: 978-3-540-31853-8
eBook Packages: Computer ScienceComputer Science (R0)