Signature Neural Networks: Definition and Application to Multidimensional Sorting Problems

In this paper we present a self-organizing neural network paradigm that is able to discriminate information locally using a strategy for information coding and processing inspired in recent findings in living neural systems. The proposed neural network uses: (1) neural signatures to identify each unit in the network; (2) local discrimination of input information during the processing; and (3) a multicoding mechanism for information propagation regarding the who and the what of the information. The local discrimination implies a distinct processing as a function of the neural signature recognition and a local transient memory. In the context of artificial neural networks none of these mechanisms has been analyzed in detail, and our goal is to demonstrate that they can be used to efficiently solve some specific problems. To illustrate the proposed paradigm, we apply it to the problem of multidimensional sorting, which can take advantage of the local information discrimination. In particular, we compare the results of this new approach with traditional methods to solve jigsaw puzzles and we analyze the situations where the new paradigm improves the performance.

[1]  Tatsuya Morita,et al.  Partial contour processing using curvature function-assembly of jigsaw puzzle and recognition of moving figures , 1986, Systems and Computers in Japan.

[2]  Michael Levison.  The Siting of Fragments , 1965, Comput. J..

[3]  Pablo Varona,et al.  Neural Signatures: Multiple Coding in Spiking–bursting Cells , 2006, Biological Cybernetics.

[4]  Margaret M. Fleck,et al.  Jigsaw puzzle solver using shape and color , 1998, ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344).

[5]  Haim J. Wolfson.  On curve matching , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Erik D. Demaine,et al.  Jigsaw Puzzles, Edge Matching, and Polyomino Packing: Connections and Complexity , 2007, Graphs Comb..

[7]  Wilfried Philips,et al.  Constructing the topological solution of jigsaw puzzles , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[8]  Kenji Shoji,et al.  Assembly of puzzles using a genetic algorithm , 2002, Object recognition supported by user interaction for service robots.

[9]  Robert Kozma,et al.  Beyond Feedforward Models Trained by Backpropagation: A Practical Training Tool for a More Efficient Universal Approximator , 2007, IEEE Transactions on Neural Networks.

[10]  Jean-Claude Fort,et al.  SOM's mathematics , 2006, Neural Networks.

[11]  D.B. Cooper,et al.  Computational reconstruction of ancient artifacts , 2008, IEEE Signal Processing Magazine.

[12]  Donald A. Sofge,et al.  Handbook of Intelligent Control: Neural, Fuzzy, and Adaptive Approaches , 1992 .

[13]  Richard Pollack,et al.  Multidimensional Sorting , 1983, SIAM J. Comput..

[14]  Tarak Gandhi,et al.  An automatic jigsaw puzzle solver , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[15]  Walid G. Aref,et al.  On Multi-dimensional Sorting Orders , 2000, DEXA.

[16]  Attila Szücs,et al.  Dopamine modulation of spike dynamics in bursting neurons , 2005, The European journal of neuroscience.

[17]  Peter Auer,et al.  A learning rule for very simple universal approximators consisting of a single layer of perceptrons , 2008, Neural Networks.

[18]  Norman I. Badler,et al.  Jigsaw puzzle matching using a boundary-centered polar encoding , 1982, Comput. Graph. Image Process..

[19]  R. D. Pinto,et al.  Synaptic modulation of the interspike interval signatures of bursting pyloric neurons. , 2003, Journal of neurophysiology.

[20]  Marshall W. Bern,et al.  A global approach to automatic solution of jigsaw puzzles , 2002, SCG '02.

[21]  Olivier D. Faugeras,et al.  HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Martin Anthony.  On the generalization error of fixed combinations of classifiers , 2007, J. Comput. Syst. Sci..

[23]  Ponnuthurai N. Suganthan.  Solving jigsaw puzzles using Hopfield neural networks , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[24]  Moshe Sipper,et al.  The preservation of favored building blocks in the struggle for fitness: the puzzle algorithm , 2004, IEEE Transactions on Evolutionary Computation.

[25]  Grigore C. Burdea,et al.  Solving jigsaw puzzles by a robot , 1989, IEEE Trans. Robotics Autom..

[26]  G. Davis.  Homeostatic control of neural activity: from phenomenology to molecular design. , 2006, Annual review of neuroscience.

[27]  Jorge Stolfi,et al.  A Multiscale Method for the Reassembly of Two-Dimensional Fragmented Objects , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  Stephan Trenn,et al.  Multilayer Perceptrons: Approximation Order and Necessary Number of Hidden Units , 2008, IEEE Transactions on Neural Networks.

[29]  Haim J. Wolfson,et al.  3-D Curve Matching , 2011 .

[30]  Ismail Hakki Toroslu,et al.  Automatic reconstruction of broken 3-D surface objects , 1999, Comput. Graph..

[31]  Horst Bunke,et al.  Jigsaw Puzzle Solving Using Approximate String Matching and Best-First Search , 1993, CAIP.

[32]  Micha Sharir,et al.  Identification of Partially Obscured Objects in Two and Three Dimensions by Matching Noisy Characteristic Curves , 1987 .

[33]  Benjamin B. Kimia,et al.  On solving 2D and 3D puzzles using curve matching , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[34]  Pablo Varona,et al.  Effect of individual spiking activity on rhythm generation of central pattern generators , 2004, Neurocomputing.

[35]  Klaus Hansen,et al.  Solving jigsaw puzzles using image features , 2008, Pattern Recognit. Lett..

[36]  A. Selverston,et al.  Dynamical principles in neuroscience , 2006 .

[37]  Pablo Varona,et al.  Reaction to neural signatures through excitatory synapses in central pattern generator models , 2007, Neurocomputing.

[38]  H. Freeman,et al.  Apictorial Jigsaw Puzzles: The Computer Solution of a Problem in Pattern Recognition , 1964, IEEE Trans. Electron. Comput..

[39]  Mu-Chun Su,et al.  A puzzle solver and its application in speech descrambling , 2007 .

[40]  H. Wolfson,et al.  Solving jigsaw puzzles by computer , 1988 .

[41]  Paul LaFollette,et al.  Isthmus critical points for solving jigsaw puzzles in computer vision , 1991, IEEE Trans. Syst. Man Cybern..

[42]  Fenghui Yao,et al.  A shape and image merging technique to solve jigsaw puzzles , 2003, Pattern Recognit. Lett..

[43]  Trevor J. Hastie,et al.  3-D curve matching using splines , 1990, J. Field Robotics.

[44]  Chaur-Chin Chen,et al.  Novel steganographic method based on jig swap puzzle images , 2009, J. Electronic Imaging.

[45]  O. Catoni.  Solving Scheduling Problems by Simulated Annealing , 1998 .