{"references": ["S. Wiggins, Introduction to Applied Nonlinear Dynamical Systems and\nChaos, (Texts in Applied Mathematics 2, Springer-Verlag)", "J. Guckenheimer and P. Holmes, Nonlinear Oscillations, Dynamical\nsystems and Bifurcations of Vector Fields (Springer, 1983)", "Pavliotis GA, Stuart AM, Multiscale Methods Averaging and\nHomogenization (New York , Springer, 2007 , ISBN: 9780387738284)", "F. Takens, Detecting strange attractors in turbulence (Dynamical\nSystems and Turbulence, Lecture Notes in Mathematics, vol. 898.\nSpringer-Verlag. pp. 366-381)", "H. E. Stanley and P. Meakin, Multifractal Phenomena in Physics and\nChemistry, Nature 335, 405-409 (1988).", "Tim Palmer, Paul Williams, Stochastic Physics and Climate Modelling\n(Royal Society Publishing, 2008, ISBN 9780854036950)", "L. A. N. Amaral, A. Scala, M. Barthelemy, and H. E. Stanley, Classes of\nBehavior of Small-World Networks (Proc. Natl. Acad. Sci. 97,\n11149-11152 (2000))", "G. Binnig et al., Will machines start to think like humans? (Europhysics\nNews (2002) Vol. 33 No. 2)", "Palmer, T. N., The Invariant Set Postulate: a new geometric framework\nfor the foundations of quantum theory and the role played by gravity\n(Proceedings of the Royal Society a Mathematical Physical and\nEngineering Sciences 465: 3165. doi:10.1098/rspa.2009.0080)\n[10] Michael F. Barnsley, Fractal Everywhere (second edition, Hawley\nRising)\n[11] Paul S. Addison, The Illustrated Wavelet Transform Handbook (Institute\nof Physics, 2002, ISBN 0-7503-0692-0)\n[12] P. Abry, P. Gon\u251c\u00baalv\u00e8s & J. L\u00e9vy-V\u00e9hel, Scaling Fractals And Wavelets\n(iSTE Publishing Company, 2005)\n[13] John C. Hart, Wayne O. Cochran, Patrick J. Flynn, Similarity Hashing: A\nComputer Vision Solution to the Inverse Problem of Linear Fractals\n(Washington State University, 2008)\n[14] C.R Handy and G. Mantica, Inverse problems in fractal construction:\nmoment method solution (Physica D 43 (1990) 17-36)\n[15] R. Rinaldo and A. Zakhor, Inverse and Approximation Problem for\nTwo-Dimensional Fractal sets (IEEE trans. on image processing, Vol.3,\nNo. 6)\n[16] R. Shonkwiler, F.Mendivil, A.Deliu, Genetic Algorithms for the 1-D\nFractal Inverse Problem (Georgia Institute of Technology)\n[17] Timothee Leleu, Akito Sakurai, Recurrent self-similarties and machine\nlearning: the inverse problem of buiding fractals (Proceedings of Mendel\n2009)\n[18] Xin Zhou and David P. Tuck, MSVM-RFE: extensions of SVM-RFE for\nmulticlass gene selection on DNA microarray data (Bioinformatics 2007\n23(9):1106-1114)\n[19] J\u00f6rg Sander, Martin Ester, Hans-Peter Kriege, Hans-Peter Kriegel,\nXiaowei Xu, Density-Based Clustering in Spatial Databases: The\nAlgorithm GDBSCAN and Its Application (Data Mining and Knowledge\nDiscovery archive, Volume 2 , Issue 2 , ISSN:1384-5810 (June 1998))\n[20] T. Kanungo, D. M. Mount, N. Netanyahu, C. Piatko, R. Silverman, and\nA. Y. Wu, A Local Search Approximation Algorithm for k-Means\nClustering (Computational Geometry: Theory and Applications, 28\n(2004), 89-112.))\n[21] Sloan's A008277, The On-Line Encyclopedia of Integer Sequences\n[22] Timothee G. Leleu, Building \"invertible\" fractals: Introduction to\nContext-Dependant Iterated Function Systems, Proc. 2010 International\nJoint Conference on Neural Networks (IJCNN 2010)\n[23] D Barbar\u251c\u00ed, P Chen, Using the fractal dimension to cluster datasets\n(Proceedings of the sixth ACM SIGKDD, 2000)\n[24] CA Duncan, MT Goodrich, SG Kobourov, Balanced aspect ratio trees\nand their use for drawing very large graphs (Lecture Notes in Computer,\nSpringer, 1998)\n[25] Michael F. Barnsley and Lyman P. Hurd, Fractal Image Compression,\nISBN 0-86720-457-5\n[26] T. Kanungo, D. M. Mount, N. Netanyahu, C. Piatko, R. Silverman, and\nA. Y. Wu, An efficient k-means clustering algorithm: Analysis and\nimplementation (IEEE Trans. Pattern Analysis and Machine\nIntelligence, 24 (2002), 881-892)\n[27] Chris Ding and Xiaofeng He, K-means Clustering via Principal\nComponent Analysis (Proc. of Int'l Conf. Machine Learning (ICML\n2004), pp 225-232. July 2004)\n[28] T. Vicsek, Fractal Growth Phenomena, 2nd ed. (World Scientific,\nSingapore 1991).\n[29] H. A. Makse, J. S. de Andrade, M. Batty, S. Havlin, and H. E. Stanley,\nModeling Urban Growth Patterns with Correlated Percolation (Phys. Rev.\nE, 1 December, 1998)"]}

A new technique of topological multi-scale analysis is introduced. By performing a clustering recursively to build a hierarchy, and analyzing the co-scale and intra-scale similarities, an Iterated Function System can be extracted from any data set. The study of fractals shows that this method is efficient to extract self-similarities, and can find elegant solutions the inverse problem of building fractals. The theoretical aspects and practical implementations are discussed, together with examples of analyses of simple fractals.