Panel Summary Perceptual Learning and Discovering

  • Salvatore Gaglio
  • Floriana Esposito
  • Stefano Nolfi


The problem of learning and discovering in perception is addressed and discussed with particular reference to present machine learning paradigms. These paradigms are briefly introduced by S. Gaglio. The subsymbolic approach is addressed by S. Nolfi, and the role of symbolic learning is analysed by F. Esposito. Many of the open problems, that are evidentiated in the course of the panel, show how this is an important field of research that still needs a lot of investigation. In particular, as a result of the whole discussion, it seems that a suitable integration of different approaches must be accurately investigated. It is observed, in fact, that the weakness of the most part of the existing systems is imputed to the existing gap between the rather ideal conditions under which most of those systems are designed to work and the very characteristics of the real world.


Unsupervised Learning Perceptual Learning Incremental Learning Input Stimulus Novelty Detection 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    J. H. Gennari, P. Langley, and D. Fisher, Models of incremental concept formation, Artificial Intelligence, Vol.40, pp. 11–61 (1989).CrossRefGoogle Scholar
  2. 2.
    J. T. Tou and R.C. Gonzalez, Pattern Recognition Principles, Addison Wesley, Reading, MA (1974).Google Scholar
  3. 3.
    D.E. Rumelhart and J.L. McClelland, Parallel Distributed Processing, Vol.1, Foundations, MIT Press, Cambridge, MA (1986).Google Scholar
  4. 4.
    L.B. Booker, D.E. Goldberg, and J.H. Holland, Classifier systems and genetic algorithms, Artificial Intelligence, Vol.40, pp. 235–282 (1989).CrossRefGoogle Scholar
  5. 5.
    K.S. Fu, Syntactic Methods in Pattern Recognition, Academic Press, New York, NY (1974).Google Scholar
  6. 6.
    P.H. Winston, Artificial Intelligence, Addison Wesley, Reading, MA (1977).Google Scholar
  7. 7.
    R.S. Michalsky, J.G. Carbonell, and T.M. Mitchell, Machine Learning-An Artificial Intelligence Approach, Springer-Verlag, Berlin, D (1984).Google Scholar
  8. 8.
    S. Minton, J.G. Carbonell, C.A. Knoblock, D.R. Kuokka, O. Etzioni, and Y. Gil, Explanation-based learning: a problem solving perspective, Artificial Intelligence, Vol.40, pp. 63–118 (1989).CrossRefGoogle Scholar
  9. 9.
    P. Langley and J.M. Zytkow, Data-driven approaches to empirical discovery, Artificial Intelligence, Vol.40, pp. 283–312 (1989).CrossRefGoogle Scholar
  10. 10.
    R.A. Brooks, Achieving artificial intelligence through building robots, A.I. Memo 899, MITAI Lab. (1986).Google Scholar
  11. 11.
    R.A. Brooks, Intelligence without representations, Artificial Intelligence, Vol.47, pp. 139–159 (1991).CrossRefGoogle Scholar
  12. 12.
    D. Parisi, F. Cecconi, and S. Nolfi, Econets: Neural networks that learn in an environment, Network, Vol. 1, pp. 149–168 (1990).CrossRefGoogle Scholar
  13. 13.
    S. Nolfi and D. Parisi, Growing neural networks, Technical Report, Institute of Psychology, Rome, I (1992).Google Scholar
  14. 14.
    I. Harvey, P. Husbands, and D. Cliff, Issue in evolutionary robotics, in Proceedings of SAB92, The Second International Conference on Simulations of Adaptive Behaviour, MIT Press Bradford Books, G.A. Meyer, H. Roitblat, and S. Wilson eds., Cambridge, MA (1993).Google Scholar
  15. 15.
    S. Nolfi and D. Parisi, Self-selection of input stimuli for improving performance, in Neural Networks and Robotics, G.A. Bekey, Kluwer Academic Publisher, Den Haag, NL (1993).Google Scholar
  16. 16.
    S. Nolfi and D. Parisi, Desired responses do not correspond to good teaching input in ecological neural networks, Technical Report, Institute of Psychology, Rome, I (1993).Google Scholar
  17. 17.
    D. Parisi and S. Nolfi, Neural Network Learning in an Ecological and Evolutionary Context, in Intelligent Perceptual Systems, V. Roberto ed., Springer-Verlag, Berlin, D, pp. 20–40 (1993).CrossRefGoogle Scholar
  18. 18.
    R.S. Michalski, A theory and methodology of inductive learning, in Machine Learning, an Artificial Intelligence Approach, R.S. Michalski, J.G. Carbonell, and T. Mitchell eds., Tioga, Palo Alto, CA, pp. 83–134 (1983).Google Scholar
  19. 19.
    T. Mitchell, R. Keller, and S. Kedar-Cabellu, Explanation-based generalization: a unifying view, Machine Learning, Vol.4, pp. 47–80 (1986).Google Scholar
  20. 20.
    Y. Kodratoff and G. Tecuci, Learning Based on Conceptual Distance, IEEE Trans. on Pattern Analysis and Machine Intelligence, PAMI-10, No.6, pp. 897–909 (1988).CrossRefGoogle Scholar
  21. 21.
    M.J. Pazzani, Integrated Learning with incorrect and Incomplete Theories, Proc. of the 5th Int. Conf. on Machine Learning, Morgan Kaufmann, Ann Arbor, MI, pp. 291–297 (1988).Google Scholar
  22. 22.
    F. Bergadano and A. Giordana, A knowledge Intensive Approach to Concept Induction, Proc. of the 5th Int. Conf. on Machine Learning, Morgan Kaufmann, Ann Arbor, MI, pp. 305–317 (1988).Google Scholar
  23. 23.
    G. Widmer, A Tight Integration of Deductive and Inductive Learning, Proc. of the 6th Int. Workshop on Machine Learning, Cornell University, Itaca, NY (1989).Google Scholar
  24. 24.
    P.H. Winston, Learning Structural Descriptions from Examples, in The Psychology of Computer Vision, P.H. Winston ed., McGraw Hill, New York, NY (1975).Google Scholar
  25. 25.
    J.H. Connell and M. Brady, Generating and Generalizing Models of Visual Objects, Artificial Intelligence, Vol.31, pp. 159–183 (1987).CrossRefGoogle Scholar
  26. 26.
    J. Segen, Graph Clustering and Model Learning by data compression, Proc. of the 7th Int. Conf. on Machine Learning, Morgan Kaufmann, Austin, TX, pp. 93–101 (1990).Google Scholar
  27. 27.
    J. Segen, GEST: a Learning Computer Vision System that Recognizes Hand Gestures, in Machine Learning IV, R.S. Michalski and G. Tecuci eds., Morgan Kaufmann, Austin, TX (1993).Google Scholar
  28. 28.
    G. Mineau, J. Gecsei, and R. Godin, Improving Consistency within Knowledge Bases, in Knowledge, Data and Computer-Assisted Decisions, M. Schader and W. Gaul eds., Springer-Verlag, Berlin, D (1990).Google Scholar
  29. 29.
    P. Torasso and L. Console, Diagnostic Problem Solving, Van Nostrand Reinhold, The Netherlands, NL (1990).Google Scholar
  30. 30.
    M. Moulet, Accuracy as a new information in law discovery, Proc. of the Conf. Symbolic/numeric Data Analysis and Learning, E. Diday ed., Nova Science Pub. (1991).Google Scholar
  31. 31.
    F. Bergadano, A. Giordana, and L. Saitta, Automated Concept Acquisition in noisy environments, IEEE Trans. on Pattern Analysis and Machine Intelligence, PAMI-10, pp. 555-578 (1988).Google Scholar
  32. 32.
    F. Esposito, D. Malerba, and G. Semeraro, Classification in noisy environments using a Distance Measure between structural symbolic descriptions, IEEE Trans. on Pattern Analysis and Machine Intelligence, PAMI-14, pp. 390-402 (1992).Google Scholar
  33. 33.
    P.H. Winston, Learning by augmenting rules and accumulating censors, in Machine Learning II, R.S. Michalski, J.G. Carbonell, and T.M. Mitchell eds., Morgan Kaufmann, Los Altos, CA (1985).Google Scholar
  34. 34.
    F. Esposito, D. Malerba, and G. Semeraro, Negation as a Specializing Operator, in Advances in Artificial Intelligence, P. Torasso ed., Lectures Notes in AI, No. 728, Springer-Verlag, Berlin, D, pp. 166–177 (1993).CrossRefGoogle Scholar
  35. 35.
    F. Esposito, D. Malerba, and G. Semeraro, Machine Learning Techniques for Knowledge Acquisition and Refinement, Proc. of the 5th Int. Conf. on Software Engineering and Knowledge Engineering, San Francisco, CA (1993).Google Scholar
  36. 36.
    J.R. Hall, Learning by Failing to Explain: Using Partial Explanations to Learn in Incomplete or Intractable Domains, Machine Learning, Vol.3, pp. 45–77 (1988).Google Scholar
  37. 37.
    J. Mostow and N. Bhatnagar, Failsafe: a Floor Planner that Uses EBG to Learn from its Failure, Proc. IJCAI87, Milano, I, pp. 249-255 (1987).Google Scholar
  38. 38.
    J.C. Schlimmer and D. Fisher, A case study for incremental concept induction, Proc. of the 5th Nat. Conf. on Artificial Intelligence, Morgan Kaufmann, pp. 496-501 (1986).Google Scholar
  39. 39.
    A.K. Jain and R.C. Dubes, Algorithms for Cluster Analysis, Prentice Hall, Englewood Cliffs, NJ (1988).Google Scholar
  40. 40.
    J.J. Mahoney and R.J. Mooney, Can Competitive Learning Compete? Comparing a Connectionist Clustering Technique to Symbolic Approach, Tech. Rep. AI89-115, University of Texas, Austin, TX (1989).Google Scholar

Copyright information

© Springer Science+Business Media New York 1994

Authors and Affiliations

  • Salvatore Gaglio
    • 1
  • Floriana Esposito
    • 2
  • Stefano Nolfi
    • 3
  1. 1.Dipartimento di Ingegneria ElettricaUniversità di PalermoPalermoItaly
  2. 2.Dipartimento di InformaticaUniversità di BariBariItaly
  3. 3.Istituto di Psicologia del CNRRomaItaly

Personalised recommendations