Skip to main content
SpringerLink
Log in

Ecological Neural Networks for Object Recognition and Generalization

  • Published:
Neural Processing Letters Aims and scope Submit manuscript

Abstract

Generalization is a critical capacity for organisms. Modeling the behavior of organisms with neural networks, some type of generalizations appear to be accessible to neural networks but other types do not. In this paper we present two simulations. In the first simulation we show that while neural networks can recognize where an object is located in the retina even if they have never experienced that object in that position ('where' generalization subtask), they have difficulty in recognizing the identity of a familiar object in a new position ('what' generalization subtask). In the second simulation we explore the hypothesis that organisms find another solution to the problem of recognizing objects in different positions on their retina: they move their eyes so that objects are always seen in the same position in the retina. This strategy emerges spontaneously in ecological neural networks that are allowed to move their 'eye' in order to bring different portions of the visible world in the central portion of their retina.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Burnham, K. P. and Anderson, D. R.:Model Selection and Inference:A Practical Information–Theoretic Approach Springer, 1998.

  2. Chapelle, O., Vapnik, V., Bousquet, O. and Mukherjee, S.:Choosing multiple parameters for support vector machines, Machine Learning 46 (1–3)(2002), 131–159.

    Google Scholar 

  3. Duan, K., Keethi, S. S. and Poo, A. N.:Evaluation of simple performance measures for tuning svm hyperparameters. Technical Report CD-01–11, Control Division, Dept. of Mechanical Engineering, National University of Singapore, 2001.

  4. Hanisch, D., Zien, A., Zimmer, R. and Lengauer, T.:Co-clustering of biological networks and gene expression data, Bioinformatics 18 (2002), S145–S154.

    Google Scholar 

  5. Kasai, H., Bairoch, A., Watanabe, K., Isono, K., Harayama, S., Gasteiger, E. and Yamamoto, S.:Construction of the gyrb database for the identification and classification of bacteria, In:Genome Informatics, 1998, pp. 13–21, Universal Academic Press, 1998.

  6. Mika, S., Rätsch, G., Weston, J., Schölkopf, B. and Müller, K.-R.:Fisher discriminant analysis with kernels, In:Y.-H. Hu, J. Larsen, E. Wilson, and S. Douglas (eds), Neural Networks for Signal Processing IX, pp. 41–48. IEEE, 1999.

  7. Pavlidis, P., Weston, J., Cai, J. and Grundy, W. N.:Gene functional classi cation from heterogeneous data, In:Proc. RECOMB2001, pp. 242–248, 2001.

  8. Pellegrini, M., Marcotte, E. M., Thompson, M. J., Eisenberg, D. and Yeates, T. O.: Assigning protein functions by comparative genome analysis:Protein phylogenetic profiles, Proc. Natl. Acad. Sci. USA 96 (8)(1999), 4285–4288.

    Google Scholar 

  9. Roth, V. and Steinhage, V.:Nonlinear discriminant analysis using kernel functions. In: S. A. Solla, T. K. Leen and K.-R. Müller (eds), Advances in Neural Information Processing Systems 12, pp. 568–574, MIT Press, 2000.

  10. Schölkopf, B. and Smola, A. J.:Learning with Kernels MIT Press, Cambridge, MA, 2001.

    Google Scholar 

  11. Schölkopf, B., Weston, J., Eskin, E., Leslie, C. and Noble, W. S.:A kernel approach for learning from almost orthogonal patterns, In:Proc. 13th European Conference on Machine Learning, pp. 511–528, 2002.

  12. Tsuda, K., Kin, T. and Asai, K.:Marginalized kernels for biological sequences, Bioinfor-matics 18 (2002), S268–S275.

    Google Scholar 

  13. Vert, J.-P. and Kanehisa, M.:Graph-driven features extraction from microarray data. Technical Report physics/0206055, Arxiv, June 2002.

  14. Watanabe, K., Nelson, J. S., Harayama, S. and Kasai, H.:ICB database:the gyrB data-base for identi cation and classification of bacteria, Nucleic Acids Res. 29 (2001), 344–345.

    Google Scholar 

  15. Yamamoto, S., Kasai, H., Arnold, D. L., Jackson, R. W., Vivian, A. and Harayama, S.: Phylogeny of the genus Pseudomonas:intrageneric structure reconstructed from the nucleotide sequences of gyrB and rpoD genes, Microbiology 146 (2000), 2385–2394.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. National Research Council, Institute of Cognitive Sciences and Technologies, Rome, Italy. e-mail

    Raffaele Calabretta, Andrea Di Ferdinando & Domenico Parisi

  2. Rome, Italy

    Andrea Di Ferdinando

  3. University of Padova, Padova, Italy

    Andrea Di Ferdinando

Authors
  1. Raffaele Calabretta
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Andrea Di Ferdinando
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Domenico Parisi
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Calabretta, R., Di Ferdinando, A. & Parisi, D. Ecological Neural Networks for Object Recognition and Generalization. Neural Processing Letters 19, 37–48 (2004). https://doi.org/10.1023/B:NEPL.0000016846.74699.1a

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/B:NEPL.0000016846.74699.1a

Search

Navigation