Learning V4 Curvature Cell Populations from Sparse Endstopped Cells

  • Antonio Rodríguez-Sánchez
  • Sabine Oberleiter
  • Hanchen Xiong
  • Justus Piater
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9887)


We investigate in this paper the capabilities of learning sparse representations from model cells that respond to curvatures. Sparse coding has been successful at generating receptive fields similar to those of simples cells in area V1 from natural images. We are interested here in neurons from intermediate areas, such as V2 and V4. Neurons on those areas are known to respond to corners and curvatures. Endstopped cells (also known as hypercomplex) are hypothesized to be selective to curvatures and are greatly represented in area V2. We propose here a sparse coding learning approach where the input is not images, nor simple cells, but curvature selective cells. We show that by learning a sparse code of endstopped cells we can obtain different degrees of curvature representations.


Sparse coding Endstopped cells Curvature Restricted Boltzmann Machine 


  1. 1.
    Hubel, D., Wiesel, T.: Receptive fields and functional architecture of monkey striate cortex. J. Physiol. 195(1), 215–243 (1968)CrossRefGoogle Scholar
  2. 2.
    von der Heydt, R., Peterhans, E., Baumgartner, G.: Illusory contours and cortical neuron responses. Science 224(4654), 1260–1262 (1984)CrossRefGoogle Scholar
  3. 3.
    Pasupathy, A., Connor, C.: Shape representation in area V4: position-specific tuning for boundary conformation. J. Neurophysiol. 86(5), 2505–2519 (2001)Google Scholar
  4. 4.
    Fukushima, K.: Neocognitron: a self organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36(4), 193–202 (1980)CrossRefzbMATHGoogle Scholar
  5. 5.
    Wei, H., Dong, Z.: V4 neural network model for visual saliency and discriminative local representation of shapes. In: 2014 International Joint Conference on Neural Networks (IJCNN), pp. 3420–3427. IEEE (2014)Google Scholar
  6. 6.
    Rodríguez-Sánchez, A., Tsotsos, J.: The roles of endstopped and curvature tuned computations in a hierarchical representation of 2D shape. PLoS ONE 7(8), 1–13 (2012)CrossRefGoogle Scholar
  7. 7.
    Olshausen, B.A., Field, D.J.: Sparse coding with an overcomplete basis set: a strategy employed by V1? Vision Res. 37, 3311–3325 (1997)CrossRefGoogle Scholar
  8. 8.
    Willmore, B., Tolhurst, D.: Characterising the sparseness of neural codes. Netw. Comput. Neural Syst. 12, 255–270 (2001)CrossRefGoogle Scholar
  9. 9.
    Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  10. 10.
    Lee, H. , Ekanadham, C. , Ng, A.Y.: Sparse deep belief net model for visual area V2. In: Advances in Neural Information Processing Systems, pp. 873–880 (2008)Google Scholar
  11. 11.
    Luo, H., Shen, R., Niu, C., Ullrich, C.: Sparse group restricted boltzmann machines. In: AAAI (2011)Google Scholar
  12. 12.
    Goh, H., Thome, N., Cord, M.: Biasing restricted Boltzmann machines to manipulate latent selectivity and sparsity. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning (2010)Google Scholar
  13. 13.
    Xiong, H., Szedmak, S., Rodríguez-Sánchez, A., Piater, J.: Towards sparsity and selectivity: Bayesian learning of restricted Boltzmann machine for early visual features. In: Wermter, S., Weber, C., Duch, W., Honkela, T., Koprinkova-Hristova, P., Magg, S., Palm, G., Villa, A.E.P. (eds.) ICANN 2014. LNCS, vol. 8681, pp. 419–426. Springer, Heidelberg (2014)Google Scholar
  14. 14.
    Rodríguez-Sánchez, A., Tsotsos, J.: The importance of intermediate representations for the modeling of 2D shape detection: endstopping and curvature tuned computations. In: CVPR, pp. 4321–4326 (2011)Google Scholar
  15. 15.
    Xiong, H., Rodríguez-Sánchez, A., Szedmak, S., Piater, J.: Diversity priors for learning early visual features. Front. Comput. Neurosci. 9(104), September 2015Google Scholar
  16. 16.
    Spitzer, H., Hochstein, S.: A complex-cell receptive-field model. J. Neurophysiol. 53(5), 1266–1286 (1985)Google Scholar
  17. 17.
    Kato, H., Bishop, P., Orban, G.: Hypeercomplex and simple/complex cells classifications in cat striate cortex. J. Neurophysiol. 41(5), 1071–1095 (1978)Google Scholar
  18. 18.
    Dobbins, A.: Difference models of visual cortical neurons. Ph.D. Dissertation, Department of Electrical Engineering. McGill University (1992)Google Scholar
  19. 19.
    Carlson, E.T., Rasquinha, R.J., Zhang, K., Connor, C.E.: A sparse object coding scheme in area V4. Curr. Biol. 21(4), 288–293 (2011)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Antonio Rodríguez-Sánchez
    • 1
  • Sabine Oberleiter
    • 1
  • Hanchen Xiong
    • 2
  • Justus Piater
    • 1
  1. 1.Institute of Computer ScienceUniversität InnsbruckInnsbruckAustria
  2. 2.Search TeamZalando SEBerlinGermany

Personalised recommendations