APM  Vol.3 No.9 A , December 2013
Hausdorff Dimension of Multi-Layer Neural Networks

This elucidation investigates the Hausdorff dimension of the output space of multi-layer neural networks. When the factor map from the covering space of the output space to the output space has a synchronizing word, the Hausdorff dimension of the output space relates to its topological entropy. This clarifies the geometrical structure of the output space in more details.

Cite this paper
J. Ban and C. Chang, "Hausdorff Dimension of Multi-Layer Neural Networks," Advances in Pure Mathematics, Vol. 3 No. 9, 2013, pp. 9-14. doi: 10.4236/apm.2013.39A1002.
[1]   K. Hornik, M. Stinchcombe and H. White, “Multilayer Feedforward Networks Are Universal Approximators,” Neural Networks, Vol. 2, No. 5, 1989, pp. 359-366.

[2]   B. Widrow and M. Lehr, “30 Years of Adaptive Neural Networks: Perceptron Madaline, and Backpropagation,” Proceedings of the IEEE, Vol. 78, No. 9, 1990, pp. 1415-1442. http://dx.doi.org/10.1109/5.58323

[3]   Y. A. Alsultanny and M. M. Aqul, “Pattern Recognition Using Multilayer Neural-Genetic Algorithm,” Neurocomputing, Vol. 51, 2003, pp. 237-247.

[4]   B. Widrow, “Layered Neural Nets for Pattern Recognition,” IEEE Transactions on Acoustics, Speech, and Signal Processing, Vol. 36, No. 7, 1962, pp. 1109-1118.

[5]   J. J. Hopeld and D. W. Tank, “Neural Computation of Decisions in Optimization Problems,” Biological Cybernetics, Vol. 52, No. 3, 1985, pp. 141-152.

[6]   C. Peterson and B. Soderberg, “A New Method for Mapping Optimization Problems onto Neural Network,” International Journal of Neural Systems, Vol. 1, 1989, pp. 3-22. http://dx.doi.org/10.1142/S0129065789000414

[7]   J.-C. Ban and C.-H. Chang, “The Learning Problem of Multi-Layer Neural Networks,” Neural Networks, Vol. 46, 2013, pp. 116-123.

[8]   J.-C. Ban, C.-H. Chang and S.-S. Lin, “The Structure of Multi-Layer Cellular Neural Networks,” Journal of Differential Equations, Vol. 252, No. 8, 2012, pp. 4563-4597.

[9]   J.-C. Ban, C.-H. Chang, S.-S. Lin and Y.-H. Lin, “Spatial Complexity in Multi-Layer Cellular Neural Networks,” Journal of Differential Equations, Vol. 246, No. 2, 2009, pp. 552-580. http://dx.doi.org/10.1016/j.jde.2008.05.004

[10]   S.-N. Chow and J. Mallet-Paret, “Pattern Formation and Spatial Chaos in Lattice Dynamical Systems: I and II,” IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications, Vol. 42, No. 10, 1995, pp. 746-756. http://dx.doi.org/10.1109/81.473583

[11]   K. Falconer, “Fractal Geometry: Mathematical Foundations and Application,” 2nd Edition, John Wilet & Sons, New York, London, Sydney, 2003.

[12]   Y. Pesin, “Dimension Theory in Dynamical Systems: Contemporary Views and Application,” The University of Chicago Press, Chicago, 1997.

[13]   J. Juang and S.-S. Lin, “Cellular Neural Networks: Mosaic Pattern and Spatial Chaos,” SIAM Journal on Applied Mathematics, Vol. 60, No. 3, 2000, pp. 891-915.

[14]   D. Lind and B. Marcus, “An Introduction to Symbolic Dynamics and Coding,” Cambridge University Press, Cambridge, 1995.

[15]   B. Kitchens, “Symbolic Dynamics. One-Sided, Two-Sided and Countable State Markov Shifts,” Springer-Verlag, New York, 1998.

[16]   J.-C. Ban and C.-H. Chang, “On the Structure of Multi-Layer Cellular Neural Networks. Part II: The Complexity between Two Layers,” Submitted, 2012.