Neural Networks for Pattern Recognition, Image and Signal Processing

  • Roberto Tagliaferri
Conference paper
Part of the Advances in Soft Computing book series (AINSC, volume 11)


In this paper Neural Networks are presented in the context of Statistical Pattern Recognition, focusing the attention on all the steps needed to classify and interpolate input data. Standard multi-layer models are briefly illustrated, and then proved to be good instruments for data interpolation and Bayesian classification. Furthermore, Neural Networks are presented in the pre-processing stage, both for input reduction and clustering. Finally, two applications to signal and image processing are summarized to show the potentiality of Neural Network based systems in real world Statistical Pattern Recognition problems.


Neural Network Weight Vector Input Pattern Principal Eigenvector Statistical Pattern Recognition 
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.
    Andreon, S., Gargiulo, G., Longo, G., Tagliaferri, R., Capuano N. (1999) Neural Networks and Star/Galaxy Separation in Wide Field Astronomical Images. Proceedings of the 1999 International Joint Conference on Neural Networks IJCNN’99, Washington, Dc, July 10–16Google Scholar
  2. 2.
    Andreon, S., Gargiulo, G., Longo, G., Tagliaferri, R., Capuano, N. (2000) Wide Field Imaging. I. Applications of Neural Networks to object detection and star/galaxy classification. Submitted to MNRAS.Google Scholar
  3. 3.
    Baldi, P., Hornik, K. (1989) Neural networks for principal component analysis: learning from examples without local minima. Neural Networks 2, 7, 53–58.CrossRefGoogle Scholar
  4. 4.
    Barone, F., De Rosa, R., Eleuteri, A., Garufi, F., Milano, L., Tagliaferri, R. (1999) A Neural Network-based ARX Model of Virgo Noise. Proceedings of the 11-th Italian Workshop on Neural Nets WIRN Vietri ‘89, M. Marinaro and R. Tagliaferri Ed.s, 171–183, Springer-Verlag, LondonCrossRefGoogle Scholar
  5. 5.
    Barone, F., Garufi, F., Milano, L., Ciaramella, A., Eleuteri, A., Tagliaferri, R. (1999) A Neural Network approach for the Noise Identification and Data Quality of the VIRGO antenna. Proceedings of the 1999 Edoardo AMALDI Conference on Gravitational Waves, California Institute of Technology, Pasadena, CA, USA, July 12–16, in press.Google Scholar
  6. 6.
    Bertin, E., Arnouts, S., 1996, AAS 117, 393.Google Scholar
  7. 7.
    Bishop, C. M. (1995) Neural Networks for Pattern Recognition. Oxford University Press, Oxford UKGoogle Scholar
  8. 8.
    Di Nola, A., Tagliaferri, R., Bélohlâvek, R., Ciaramella, A. (2000) Fuzzy Neural Networks Based on Fuzzy Logic Algebras Valued Relations. DMI Soft-computing Lab, Int. Report.Google Scholar
  9. 9.
    Everitt B. (1977) Cluster Analysis Social Science Research Council. Heinemann Educational Books, LondonGoogle Scholar
  10. 10.
    Fisher, R. A. (1936) The use of multiple measurements in taxonomic problems. Annals of Eugenica 7, 179–188CrossRefGoogle Scholar
  11. 11.
    Fritzke, B. (1994) Growing Cell Structures–A Self-Organizing Network for Unsupervised and Supervised Learning. Neural Networks, 7, 9, 1441–1460CrossRefGoogle Scholar
  12. 12.
    Girosi, F., Poggio, T. (1990) Neural Networks and the best approximation property. Biological Cybernetics 63, 169–176MathSciNetMATHCrossRefGoogle Scholar
  13. 13.
    Infante, L., Pritchet, C. (1992) ApJS, 83, 237CrossRefGoogle Scholar
  14. 14.
    Jarvis, J. F., Tyson, J. A. (1981) AJ, 86, 476.CrossRefGoogle Scholar
  15. 15.
    Jollife, I. T. (1986) Principal Component Analysis. Springer—Verlag, New YorkCrossRefGoogle Scholar
  16. 16.
    Jutten, C., Herault, J. (1991) Blind separation of sources, paru: an adaptive algorithm based on neuromimetic architecture. Signal Processing, 24, 1, 1–10MATHCrossRefGoogle Scholar
  17. 17.
    Karhunen, J., Joutsensalo, J. (1994) Representation and separation of signals using nonlinear PCA type learning. Neural Networks 7, 113–127CrossRefGoogle Scholar
  18. 18.
    Karhunen, J. Joutsensalo, J. (1995) Generalization of principal component analysis, optimization problems, and neural networks. Neural Networks 8 549562Google Scholar
  19. 19.
    Kay, S. M. (1988) Modern spectral estimation: theory and application. Englewood Cliffs: Prentice-HallMATHGoogle Scholar
  20. 20.
    Koh, J., Suk, M., Bhandarkar, S. (1995) A Multilayer Self-Organizing Feature Map for Range Image Segmentation. Neural Networks 8, 1, 67–86.CrossRefGoogle Scholar
  21. 21.
    Kohonen, T. (1982) Self-organized formation of topologically correct feature maps. Biological Cybernetics 43, 59–69MathSciNetMATHCrossRefGoogle Scholar
  22. 22.
    Kohonen, T. (1988) Self-organization and associative memory ( 2nd edition ). Springer-Verlag, BerlinMATHCrossRefGoogle Scholar
  23. 23.
    Lloyd, S. (1982) Least squares quantization in PCM. IEEE Transactions on Information Theory IT-28, 2Google Scholar
  24. 24.
    Martinetz, T., Berkovich, S., Schulten, K. (1993) Neural-Gas Network for Vector Quantization and its Application to Time-Series Prediction. IEEE Transactions on Neural Networks 4, 4, 558–568CrossRefGoogle Scholar
  25. 25.
    Marple, S. L. (1987) Digital spectral analysis with applications. Prentice-Hall, Englewood Cliffs, N. Y.Google Scholar
  26. 26.
    Meneganti, M., Saviello, F., Tagliaferri, R. (1998) Fuzzy Neural Networks for Classification and Detection of Anomalies. IEEE Transactions on Neural Networks special issue on “Neural Networks and Hybrid Intelligent Models: Foundations, Theory and Applications” 9, 5, 848–861Google Scholar
  27. 27.
    Narendra, P. M., Fukunaga, K. (1977) A branch and bound algorithm for feature subset selection. IEEE Trans. on Computers 26, 9, 917–922MATHCrossRefGoogle Scholar
  28. 28.
    Oja, E. (1982) A simplified neuron model as a principal component analyzer. Journal of Mathematical Biology 15, 267–273MathSciNetMATHCrossRefGoogle Scholar
  29. 29.
    Oja, E., Ogawa, H., Wangviwattana, J. (1991) Learning in nonlinear constrained Hebbian network. Artificial neural networks, T. Kohonen etal. (Eds.), 385–390, North-Holland, AmsterdamGoogle Scholar
  30. 30.
    Oja, E., Karhunen, J., Wang, L., Vigario, R. (1996) Principal and independent components in neural networks–recent developments. In Seventh Italian Workshop on Neural Networks, WIRN Vietri’95, M.Marinaro and R.Tagliaferri Ed.s, 16–35, World Scientific Pu. SingaporeGoogle Scholar
  31. 31.
    Plumbley, M. (1993) Hebbian/anti Hebbian network which optimizes information capacity by orthonormalizing the principal subspace. Proc. IEE Conf. on Artificial Neural Networks, Brighton, UK, 86–90Google Scholar
  32. 32.
    Rose, K., Gurewitz, F., Fox, G. (1990) Statistical mechanics and phase transition in clustering. Phys. Rev. Lett. 65, 945–948CrossRefGoogle Scholar
  33. 33.
    Rumelhart, D. E., Hinton, G. E., Williams, R. J. (1986) Learnig internal representation by error propagation, in Parallel Distributed Processing: Explorations in the Microstructure of of Cognition, Volume 1: Foundations, D. E. Rumelhart, J. L. McClelland and the PDP group Ed.s, 318–362, MIT Press, Cambridge, MAGoogle Scholar
  34. 34.
    Sanger, T. D. (1989) Optimal unsupervised learning in a single-layer linear feedforward network, Neural Network, 2, 459–473CrossRefGoogle Scholar
  35. 35.
    Tagliaferri, R., Longo, G., Andreon, S., Zaggia, S., Capuano, N., Gargiulo, G. (1998) Astronomical Object Recognition by Means of Neural Networks. Proceedings of the 10-th Italian Workshop on Neural Nets WIRN, Marinaro M. and Tagliaferri R. Ed.s, 169–178, Springer-Verlag, LondonGoogle Scholar
  36. 36.
    Tagliaferri, R., Capuano, N., Gargiulo, G. (1999) Automated Labeling for Unsupervised Neural Networks: A Hierarchical Approach. IEEE Transactions on Neural Networks 10, 199–203CrossRefGoogle Scholar
  37. 37.
    Tagliaferri, R., Ciaramella, A., Milano, L., Barone, F., Longo, G. (1999) Spectral Analysis of Stellar Light Curves by Means of Neural Networks. Astronomy and Astrophysics Supplement Series, 137, 391–405CrossRefGoogle Scholar
  38. 38.
    Tagliaferri, R., Eleuteri, A., Meneganti, M., Barone, F. (2000) Fuzzy Min-Max Neural Networks: from Classification to Regression. Soft Computing, in pressGoogle Scholar
  39. 39.
    Tagliaferri, R., Pelosi, N., Ciaramella, A., Barone, F., Milano, M. (2000) Soft Computing Methodologies for Spectral Analysis in Cyclostratigraphy. Computers and Geosciences, in pressGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Roberto Tagliaferri
    • 1
    • 2
    • 3
  1. 1.Dip. di Matematica e Informatica, Soft-Computing Lab.Università di SalernoBaronissi (SA)Italy
  2. 2.INFMunità di SalernoBaronissi (SA)Italy
  3. 3.IIASS“E. R. Caianiello”Vietri s/m (SA)Italy

Personalised recommendations