Advertisement

Local Context Discrimination in Signature Neural Networks

  • Roberto Latorre
  • Francisco B. Rodríguez
  • Pablo Varona
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6687)

Abstract

Bio-inspiration in traditional artificial neural networks (ANN) relies on knowledge about the nervous system that was available more than 60 years ago. Recent findings from neuroscience research provide novel elements of inspiration for ANN paradigms. We have recently proposed a Signature Neural Network that uses: (i) neural signatures to identify each unit in the network, (ii) local discrimination of input information during the processing, and (iii) a multicoding mechanism for information propagation regarding the who and the what of the information. The local discrimination implies a distinct processing as a function of the neural signature recognition and a local transient memory. In this paper we further analyze the role of this local context memory to efficiently solve jigsaw puzzles.

Keywords

Bioinspired ANNs Neural signatures Multicoding Local discrimination Local contextualization 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Fort, J.: Som’s mathematics. Neural Networks 19(6-7), 812–816 (2006); Advances in Self Organising Maps - WSOM 2005CrossRefzbMATHGoogle Scholar
  2. 2.
    Anthony, M.: On the generalization error of fixed combinations of classifiers. Journal of Computer and System Sciences 73(5), 725–734 (2007)MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Trenn, S.: Multilayer perceptrons: Approximation order and necessary number of hidden units. IEEE Trans. Neural Netw. 19(5), 836–844 (2008)CrossRefGoogle Scholar
  4. 4.
    Auer, P., Burgsteiner, H., Maass, W.: A learning rule for very simple universal approximators consisting of a single layer of perceptrons. Neural Networks 21(5), 786–795 (2008)CrossRefzbMATHGoogle Scholar
  5. 5.
    Ilin, R., Kozma, R., Werbos, P.: Beyond feedforward models trained by backpropagation: A practical training tool for a more efficient universal approximator. IEEE Trans. Neural Netw. 19(6), 929–937 (2008)CrossRefGoogle Scholar
  6. 6.
    White, D.A., Sofge, A. (eds.): Handbook of Intelligent Control Neural, Fuzzy, and Adaptive Approaches. Reinhold, NewYork (1992)Google Scholar
  7. 7.
    Szücs, A., Pinto, R.D., Rabinovich, M.I., Abarbanel, H.D.I., Selverston, A.I.: Synaptic modulation of the interspike interval signatures of bursting pyloric neurons. J. Neurophysiol. 89, 1363–1377 (2003)CrossRefGoogle Scholar
  8. 8.
    Szücs, A., Abarbanel, H.D.I., Rabinovich, M.I., Selverston, A.I.: Dopamine modulation of spike dynamics in bursting neurons. Eur. J. Neurosci. 2, 763–772 (2005)CrossRefGoogle Scholar
  9. 9.
    Latorre, R., Rodríguez, F.B., Varona, P.: Effect of individual spiking activity on rhythm generation of Central Pattern Generators. Neurocomputing 58-60, 535–540 (2004)CrossRefGoogle Scholar
  10. 10.
    Latorre, R., Rodríguez, F.B., Varona, P.: Neural signatures: multiple coding in spiking-bursting cells. Biol. Cybern. 95, 169–183 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  11. 11.
    Latorre, R., Rodríguez, F.B., Varona, P.: Reaction to neural signatures through excitatory synapses in Central Pattern Generator models. Neurocomputing 70, 1797–1801 (2007)CrossRefGoogle Scholar
  12. 12.
    Baroni, F., Torres, J.J., Varona, P.: History-Dependent Excitability as a single-cell substrate of transient memory for information discrimination. PLoS ONE 5(12), e15023 (2010)Google Scholar
  13. 13.
    Latorre, R., Rodríguez, F.B., Varona, P.: Signature Neural Networks: Definition and Application to Multidimensional Sorting Problems. IEEE Trans. Neural Netw. 22(1), 8–23 (2011)CrossRefGoogle Scholar
  14. 14.
    Yao, F., Shao, H.: A shape and image merging technique to solve jigsaw puzzles. Pattern Recogn. Lett. 24(12), 1819–1835 (2003)CrossRefGoogle Scholar
  15. 15.
    Freeman, H., Gardner, L.: Apictorial Jigsaw Puzzles: A Computer Solution to a Problem in Pattern Recognition. IEEE Trans. Electron. Comput. EC-13, 118–127 (1964)CrossRefGoogle Scholar
  16. 16.
    Wolfson, H., Schonberg, E., Kalvin, A., Landam, Y.: Solving jigsaw puzzles by computer. Ann. Oper. Res. 12, 51–64 (1988)MathSciNetCrossRefGoogle Scholar
  17. 17.
    Goldberg, D., Malon, C., Bern, M.: A global approach to automatic solution of jigsaw puzzles. Computational Geometry 28, 165–174 (2004)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Bunke, H.,, Kaufmann, G.: Jigsaw Puzzle Solving Using Approximate String Matching and Best-First Search. In: Chetverikov, D., Kropatsch, W.G. (eds.) CAIP 1993. LNCS, vol. 719, pp. 299–308. Springer, Heidelberg (1993)CrossRefGoogle Scholar
  19. 19.
    Kong, W., Kimia, B.B.: On solving 2D and 3D puzzles using curve matching. In: Proc. IEEE Computer Vision and Pattern Recognition (2001)Google Scholar
  20. 20.
    Levison, M.: The Siting of Fragments. Computer Journal 7, 275–277 (1965)CrossRefGoogle Scholar
  21. 21.
    Demaine, E.D., Demaine, M.L.: Jigsaw puzzles, edge matching, and polyomino packing: Connections and complexity. Graph. Comb. 23(1), 195–208 (2007)MathSciNetCrossRefzbMATHGoogle Scholar
  22. 22.
    Rabinovich, M.I., Varona, P., Selverston, A.I., Abarbanel, H.D.I.: Dynamical principles in neuroscience. Reviews of Modern Physics 78, 1213–1265 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Roberto Latorre
    • 1
  • Francisco B. Rodríguez
    • 1
  • Pablo Varona
    • 1
  1. 1.Grupo de Neurocomputación Biológica, Dpto. de Ingeniería Informática, Escuela Politécnica SuperiorUniversidad Autónoma de MadridMadridSpain

Personalised recommendations