A novel artificial neural network for sorting

An artificial neural network (ANN) is employed for sorting a sequence of real elements in monotonic (descending or ascending) order. Although inspired by harmony theory (HT), whereby the same construction as for the HT ANN is followed, the proposed ANN differs in the mode of operation, namely the obliteration of the consensus (harmony) function, the circumvention of simulated annealing as a means of settling to a solution, the simplification of the activation updating of the nodes of the upper layer, the clamping of the nodes of the lower layer, the gradual shrinking of the ANN and the use of an automatic termination criterion. The creation of the sorted sequence is progressive, whereby at most as many network updates are required as there are elements in the sequence. Ties between elements are resolved by simultaneous activation of the corresponding nodes. Finally, the min and max problems are solved in a single network update.

[1]  S. Lakshmivarahan,et al.  Parallel Sorting Algorithms , 1984, Adv. Comput..

[2]  D. T. LEE,et al.  An On-Chip Compare/Steer Bubble Sorter , 1981, IEEE Transactions on Computers.

[3]  C.F.N. Cowan,et al.  Adaptive equalization of finite nonlinear channels using multilayer perceptron , 1990 .

[4]  Jun Wang.  Analysis and design of an analog sorting network , 1995, IEEE Trans. Neural Networks.

[5]  Yoshiyasu Takefuji.  A two-step parallel sorting algorithm based on neural networks , 1990 .

[6]  George Tambouratzis,et al.  Neural network versus statistical clustering techniques: a pilot study in a phoneme recognition task , 1997 .

[7]  Rhys S. Francis,et al.  A Benchmark Parallel Sort for Shared Memory Multiprocessors , 1988, IEEE Trans. Computers.

[8]  Tatiana Tambouratzis,et al.  A simulated annealing artificial neural network implementation of the n-queens problem , 1997, Int. J. Intell. Syst..

[9]  M. Malek,et al.  A Fault-Tolerant Systolic Sorter , 1988, IEEE Trans. Computers.

[10]  Donald E. Knuth,et al.  The art of computer programming: sorting and searching (volume 3) , 1973 .

[11]  R. Brockett.  Dynamical systems that sort lists, diagonalize matrices, and solve linear programming problems , 1991 .

[12]  Donald E. Knuth,et al.  The Art of Computer Programming: Volume 3: Sorting and Searching , 1998 .

[13]  G. J. Gibson,et al.  Adaptive channel equaliza-tion using a polynomial-perceptron structure , 1990 .

[14]  James L. McClelland,et al.  Information Processing in Dynamical Systems: Foundations of Harmony Theory , 1987 .

[15]  T. Tambouratzis.  Decomposition co-ordination artificial neural network for satellite broadcast scheduling , 1998 .

[16]  Jehoshua Bruck,et al.  Neural computation of arithmetic functions , 1990 .

[17]  Wen-Tsuen Chen,et al.  A neural sorting network with O(1) time complexity , 1990, IJCNN.

[18]  Dharma P. Agrawal,et al.  Efficient sorting with CCD's and magnetic bubble memories , 1981, IEEE Transactions on Computers.

[19]  Tatiana Tambouratzis.  A simulated annealing artificial neural network implementation of the n‐queens problem , 1997 .

[20]  Franco P. Preparata,et al.  A Minimum Area VLSI Network for O(log n) Time Sorting , 1985, IEEE Transactions on Computers.

[21]  Vishwani D. Agrawal,et al.  An Information Theoretic Approach to Digital Fault Testing , 1981, IEEE Transactions on Computers.

[22]  M. Atkins,et al.  Sorting by Hopfield net , 1989, International 1989 Joint Conference on Neural Networks.

[23]  Paul Smolensky,et al.  Information processing in dynamical systems: foundations of harmony theory , 1986 .

[24]  Yuen-Hsien Tseng,et al.  Solving sorting and related problems by quadratic perceptrons , 1992 .

[25]  Taek Mu Kwon,et al.  A parallel sorting network without comparators: A neural network approach , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[26]  L. Faybusovich.  Dynamical systems that solve linear programming problems , 1992, [1992] Proceedings of the 31st IEEE Conference on Decision and Control.

[27]  Nicola Santoro,et al.  Distributed Sorting , 1985, IEEE Transactions on Computers.

[28]  T. Tambouratzis.  Edge crossing minimisation using artificial neural networks , 1997 .

[29]  T Tambouratzis.  An implementation of a harmony theory network for interpreting line-drawings , 1991 .

[30]  C.F.N. Cowan,et al.  The application of nonlinear structures to the reconstruction of binary signals , 1991, IEEE Trans. Signal Process..

[31]  Yoshiyasu Takefuji,et al.  A super-parallel sorting algorithm based on neural networks , 1990 .

[32]  Tatiana Tambouratzis.  A consensus-function artificial neural network for map-coloring , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[33]  Pietro Burrascano,et al.  A neural technique for satellite coverage plans optimization , 1992 .

[34]  Viktor K. Prasanna,et al.  Optimal VLSI Sorting with Reduced Number of Processors , 1991, IEEE Trans. Computers.