A Continuous-Time Model of Analogue K-Winners-Take-All Neural Circuit
A continuous-time model of analogue K-winners-take-all (KWTA) neural circuit which is capable to extraction the K largest from any finite value N unknown distinct inputs, where 1 ≤ K < N, is presented. The model is described by one state equation with discontinuous right-hand side and output equation. A corresponding functional block diagram of the model is given as N feedforward and one feedback hardlimiting neurons, which is used to determine the dynamic shift of inputs. The model combines such properties as high accuracy and convergence speed, low computational and hardware implementation complexity, and independency on initial conditions. Simulation examples demonstrating the model performance are provided.
KeywordsContinuous-time model State equation Functional block-diagram Hardlimiting neuron Analogue K-winners-take-all neural circuit
Unable to display preview. Download preview PDF.
- 1.Majani, E., Erlanson, R., Abu-Mostafa, Y.: On the K-winners-take-all network. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing Systems, vol. 1, pp. 634–642. Morgan Kaufmann Publishers Inc., San Francisco (1989)Google Scholar
- 2.Atkins, M.: Sorting by Hopfield nets. In: IEEE Int. Joint Conf. on Neural Networks, pp. 65–68. IEEE Press (1982)Google Scholar
- 8.Erlanson, R., Abu-Mostafa, Y.: Analog neural networks as decoders. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing Systems, vol. 1, pp. 585–588. Morgan Kaufmann Publishers Inc., San Francisco (1991)Google Scholar
- 9.Fish, A., Akselrod, D., Yadid-Pecht, O.: High precision image centroid computation via an adaptive k-winner-take-all circuit in conjunction with a dynamic element matching algorithm for star tracking applications. Analog Integrated Circuits and Signal Processing 39, 251–266 (2004)CrossRefGoogle Scholar
- 16.Tymoshchuk, P.V.: A dynamic K-winners take all analog neural circuit. In: IVth IEEE Int. Conf. “Perspective Technologies and Methods in MEMS Design”, pp. 13–18. IEEE Press, L’viv (2008)Google Scholar
- 18.Tymoshchuk, P.V.: Stability analysis of continuous-time model of K-Winners-Take-All neural circuit. In: XVI Ukrainian-Polish Conf. “CAD in Machinery Design. Implementation and Educational Problems”, pp. 29–30. IEEE Press, L’viv (2008)Google Scholar