Meta-learning

  • Objective: meta-learning approaches, or learning how to learn.
  • Participants: Wlodzislaw Duch, Norbert Jankowski, Krzysztof Gr¹bczewski, Marek Grochowski, Tomasz Maszczyk, former: Karol Grudzinski (1998-2002)
  • Time: started in 2000 with papers on similarity-based learning, with some preliminary work on heterogenous systems already in 1995
  • Results: papers below; for more papers see the list here, some talks on this topic are on this list.

    Books/chapters:

    Papers:

    Papers related to heterogenous systems are also relevant here:

    1. Duch W (2005) Uncertainty of data, fuzzy membership functions, and multi-layer perceptrons.
      IEEE Transactions on Neural Networks 16(1): 10-23.
      Relations between fuzzy logic and neural transfer functions are analyzed and a few new transfer functions derived.
    2. Jankowski N, Gr¹bczewski K, Heterogenous Committees with Competence Analysis, Fifth International conference on Hybrid Intelligent Systems, Rio de Janeiro, Brasil, 2005, pp. 417-422.

    3. Duch W, Jankowski N, Transfer functions: hidden possibilities for better neural networks. 9th European Symposium on Artificial Neural Networks (ESANN), Brugge 2001. De-facto publications, pp. 81-94
    4. Duch W, Adamczak R, Diercksen GHF, Constructive density estimation network based on several different separable transfer functions. 9th European Symposium on Artificial Neural Networks (ESANN), Brugge 2001. De-facto publications, pp. 107-112
    5. Jankowski N, Duch W, Optimal transfer function neural networks. 9th European Symposium on Artificial Neural Networks (ESANN), Brugge 2001. De-facto publications, pp. 101-106
    6. Duch W, Adamczak R, Diercksen GHF, Neural Networks from Similarity Based Perspective.
      New Frontiers in Computational Intelligence and its Applications. Ed. M. Mohammadian, IOS Press, Amsterdam 2000, pp. 93-108
    7. Duch W, Jankowski N, Taxonomy of neural transfer functions,
      IEEE, International Joint Conference on Neural Networks 2000 (IJCNN), Vol. III, pp. 477-484
    8. Duch W, Jankowski N (1999) Survey of neural transfer functions,
      Neural Computing Surveys 2: 163-213, paper in PDF.
    9. Duch W, Adamczak R, Diercksen GHF (1999) Neural Networks in non-Euclidean spaces.
      Neural Processing Letters  10: 201-210
    10. Duch W, Adamczak R, Diercksen GHF (1999) Distance-based multilayer perceptrons.
      Computational Intelligence for Modelling Control and Automation. Neural Networks and Advanced Control Strategies. Ed. M. Mohammadian, IOS Press, Amsterdam, pp. 75-80
    11. Duch W and Jankowski N (1996) Bi-radial transfer functions. | PDF file.
      Proceedings of the Second Conference on Neural Networks and their applications, Orle Gniazdo, 30.IV-4.V.1996, pp. 131-137


    Other papers related to heterogenous systems:

    1. Kordos M, Duch W (2004), A Survey of Factors Influencing MLP Error Surface.
      Control and Cybernetics 33(4): 611-631.
      Neural error functions are influence by the choice of transfer functions, but the primary goal here is to visualize the training process.
    2. Duch W, Blachnik M, Fuzzy rule-based systems derived from similarity to prototypes.
      Lecture Notes in Computer Science, Vol. 3316 (2004) 912-917.
      Introduces transformations between distance functions and fuzzy membership functions that are used as transfer functions in the basis expansion networks, such as RBF or separable functions networks.
    3. Duch W, Grabczewski K, Heterogeneous adaptive systems. IEEE World Congress on Computational Intelligence, Honolulu, May 2002, pp. 524-529.
    4. Duch W, Similarity based methods: a general framework for classification, approximation and association,
      Control and Cybernetics 29 (4) (2000) 937-968
    5. Duch W, Adamczak R, Diercksen G.H.F, Classification, Association and Pattern Completion using Neural Similarity Based Methods.
      Applied Mathematics and Computer Science 10:4 (2000) 101-120
    6. N. Jankowski. Ontogenic neural networks and their applications to classification of medical data . PhD thesis, Department of Computer Methods, Nicolaus Copernicus University, Torun, Poland, 1999.
    7. N. Jankowski. Approximation and classification in medicine with IncNet neural networks. In Machine Learning and Applications. Workshop on Machine Learning in Medical Applications, pp. 53-58, Chania, Greece, July 1999.
    8. N. Jankowski. Flexible transfer functions with ontogenic neural. Technical report, Computational Intelligence Lab, DCM NCU, Torun, Poland, 1999.
    9. N. Jankowski. Approximation with RBF-type neural networks using flexible local and semi-local transfer functions. In 4th Conference on Neural Networks and Their Applications, pp. 77-82, Zakopane, Poland, May 1999.
    10. Duch W, Grudzinski K and Diercksen G.H.F (1998) Minimal distance neural methods.
      World Congress of Computational Intelligence, May 1998, Anchorage, Alaska, IEEE IJCNN'98 Proceedings, pp. 1299-1304
    11. Duch W and Jankowski N (1997) New neural transfer functions.
      Applied Mathematics and Computer Science 7 (1997) 639-658 (invited by the Editor)
    12. Duch W and Diercksen GHF (1995) Feature Space Mapping as a universal adaptive system. | PDF file
      Computer Physics Communications 87: 341-371
    13. Duch W (1994) Floating Gaussian Mapping: a new model of adaptive systems.
      Neural Network World 4:645-654
    14. Duch W (1993) On the optimal processing functions for neural network elements, UMK-KMK-TR 6/93 report.
    15. Links to many talks and to other papers on various subjects.
  • Open problems: applications, theory.

  •  
  • Back to Dept. of Informatics list of projects

  •