Stable computational dynamics for a class of circuits with O(N) interconnections capable of KWTA and rank extractions

A new dynamical system and computational circuit is described and analyzed. The dynamics permits the construction of a Lyapunov function that ensures global convergence to a unique stable equilibrium. The analog circuit realization is of the neural network type, with N cells represented by high-gain amplifiers, global feedback, and at most 2N interconnections, where N is the number of inputs. A specific application (called "the K-selector") which signals the ranks of the K largest elements of input list and, in parallel the rank of the (K+1)th element, is designed and numerically tested. For a given density of the input elements, one obtains feasible separation intervals of output signals, i.e., good processing performances. The circuit requires an appropriate control source and suitable scaling of the input data.

[1]  Yaser S. Abu-Mostafa,et al.  Analog Neural Networks as Decoders , 1990, NIPS.

[2]  B. Sekerkiran,et al.  A CMOS K-winners-take-all circuit with O(n) complexity , 1999 .

[3]  Corneliu A. Marinov,et al.  Another K-winners-take-all analog neural network , 2000, IEEE Trans. Neural Networks Learn. Syst..

[4]  Stephen M. Walters,et al.  Neural network architecture for crossbar switch control , 1991 .

[5]  R. Priemer,et al.  Collective process circuit that sorts , 1997 .

[6]  James M. Ortega,et al.  Iterative solution of nonlinear equations in several variables , 2014, Computer science and applied mathematics.

[7]  Corneliu A. Marinov,et al.  Performance analysis for a K-winners-take-all analog neural network: basic theory , 2003, IEEE Trans. Neural Networks.

[8]  Yuguang Fang,et al.  Dynamics of a Winner-Take-All Neural Network , 1996, Neural Networks.

[9]  Fathi M. A. Salam,et al.  On the analysis of dynamic feedback neural nets , 1991 .

[10]  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.

[11]  John Lazzaro,et al.  Winner-Take-All Networks of O(N) Complexity , 1988, NIPS.

[12]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

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

[14]  J. J. Hopfield,et al.  “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.

[15]  Andrew Chi-Sing Leung,et al.  Analysis for a class of winner-take-all model , 1999, IEEE Trans. Neural Networks.

[16]  M. Vidyasagar.  Minimum-seeking properties of analog neural networks with multilinear objective functions , 1993, Proceedings of 32nd IEEE Conference on Decision and Control.

[17]  Boon Poh Tan,et al.  Semiparallel rank order filtering in analog VLSI , 2001 .

[18]  A. Michel,et al.  Analysis and synthesis of a class of neural networks: linear systems operating on a closed hypercube , 1989 .

[19]  John J. Hopfield,et al.  Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit , 1986 .

[20]  Tan Xiao.  Global Exponential Stability of Hopfield Neural Networks , 2005 .

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

[22]  Jun Wang,et al.  Absolute exponential stability of a class of continuous-time recurrent neural networks , 2003, IEEE Trans. Neural Networks.

[23]  C. A. Desoer,et al.  Nonlinear Systems Analysis , 1978 .

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

[25]  Tharam S. Dillon,et al.  Exponential stability and oscillation of Hopfield graded response neural network , 1994, IEEE Trans. Neural Networks.

[26]  Yoram Baram,et al.  Second-order bounds on the domain of attraction and the rate of convergence of nonlinear dynamical systems and neural networks , 1994, IEEE Trans. Neural Networks.

[27]  Yaser S. Abu-Mostafa,et al.  On the K-Winners-Take-All Network , 1988, NIPS.

[28]  I. E. Opris,et al.  Analog rank extractors , 1997 .

[29]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[30]  Mahesan Niranjan,et al.  A theoretical investigation into the performance of the Hopfield model , 1990, IEEE Trans. Neural Networks.