Описується математична модель KWTA-нейронної схеми («K-winners-take-all»), призначеної для ідентифікації К максимальних серед N невідомих, змінних у часі дискретизованих сигналів, де $1 \leq \mathrm{K}<\mathrm{N}$. Для коректного функціонування моделі динамічний зсув вхідних сигналів протягом перехідних процесів повинен змінюватись набагато швидше, ніж вхідні сигнали. Представлено відповідні результати комп’ютерного моделювання.
Mathematical model of discrete-time KWTA-neural circuit (K-winners-take-all) that can identify K maximal among N unknown, variable in time sampled signals, where $1 \leq \mathrm{K}<\mathrm{N}$ is described. In order to have correct model functioning a dynamic shift of input signals should be changed much faster than input signals during transients. Corresponding computer modeling results are given.
- .Bihn L. N. and Chong, H. C. A neural-network contention controller for packet switching networks, IEEE Trans. on Neural Networks 6 (1995) 1402-1410.
- David H.A. Order Statistics, 2nd ed.(New York: Wiley, 1980).
- Hu X. and Wang J. An improved dual neural network for solving a class of quadratic programming problems and its k-winners-take-all application, IEEE Trans. on Neural Networks, 19 (2008) 2022-2031.
- Kwon T. M. and Zervakis M. A parallel sorting network without comparators: A neural-network approach, in: Proc. Int. Joint Conf. on Neural Networks, Vol. 1 (1992) 701-706.
- Lippmann R. P., Gold B. and Malpass M.L. A comparison of Hamming and Hopfield neural nets for pattern classification, MIT Lincoln Laboratory Technical report TR-769 (1987) 1-37.
- Liu S. and Wang J. A simplified dual neural network for quadratic programming with its KWTA application, IEEE Trans. on Neural Networks, 17 (2006) 1500-1510.
- Marinov C. A. and Hopfield J. J. Stable computational dynamics for a class of circuits with 0(N) interconnections capable of KWTA and rank extractions, IEEE Trans. on Cir. and Syst. I: Fundamental Theory and Applications 52 (2005) 949-959.
- Tymoshchuk P. and Kaszkurewicz E. A Winner-take-all circuit based on second order Hopfield neural networks as building blocks, in: Proc. Int. Joint Conf. on Neural Networks, Vol. II (2003) 891-896.
- Tymoshchuk P. and Kaszkurewicz E. A winner-take-all circuit using neural networks as building blocks, Neurocomputing 64 (2005) 375-396.
- Urahama K. and Nagao T. K-Winner-take-all circuit with 0(n) complexity, IEEE Trans. on Neural Networks 6 (1995) 776-778.
- Yang J. F. and Chen C. M. A Dynamic K-Winners-Take- All Neural Network, IEEE Trans. on Syst., Man and Cyb. 27 (1997) 523~526.
- Yen J. C., Guo J. I. and Chen H.-C. A new k -Winners-take all neural network and its array architecture, IEEE Trans. on Neural Networks 9 (1998) 901-912.