Паралельне фільтрування рангу на основі імпульсної нейронної мережі типу “K-WINNERS-TAKE-ALL”

dc.citation.epage165
dc.citation.issue881
dc.citation.journalTitleВісник Національного університету «Львівська політехніка». Серія: Комп’ютерні системи та мережі
dc.citation.spage160
dc.contributor.affiliationНаціональний університет “Львівська політехніка”
dc.contributor.affiliationLviv Polytechnic National University
dc.contributor.authorТимощук, П. В.
dc.contributor.authorTymoshchuk, P. V.
dc.coverage.placenameЛьвів
dc.date.accessioned2018-09-25T08:55:57Z
dc.date.available2018-09-25T08:55:57Z
dc.date.created2017-03-28
dc.date.issued2017-03-28
dc.description.abstractПредставлено нейронну мережу (НМ) неперервного часу типу “K-winners-take-all” (KWTA), яка ідентифікує К найбільші з-поміж N входів, де керуючий сигнал 1 £ K < N . Мережа описується рівнянням стану з розривною правою частиною і вихідним рівнянням. Рівняння стану містить шлейф імпульсів, які описуються сумою дельта- функцій Дірака. Головною перевагою мережі порівняно з іншими близькими аналогами є відсутність обмежень на швидкість збіжності. Описано застосування мережі для паралельного фільтрування рангу. Отримані теоретичні результати проілюстровано прикладом комп’ютерного моделювання, який демонструє ефективність мережі.
dc.description.abstractA continuous-time K-winners-take-all (KWTA) neural network (NN) which is capable of identifying the largest K of N inputs, where a command signal 1 £ K < N has presented. The network is described by a state equation with a discontinuous right-hand side and by an output equation. The state equation contains an impulse train defined by a sum of Dirac delta functions. The main advantage of the network is not subject to the intrinsic convergence speed limitations of comparable designs. Application of the network for parallel rank-order filtering has described. Theoretical results are derived and illustrated with computer simulation example that demonstrates the network’s performance.
dc.format.extent160-165
dc.format.pages6
dc.identifier.citationТимощук П. В. Паралельне фільтрування рангу на основі імпульсної нейронної мережі типу “K-WINNERS-TAKE-ALL” / П. В. Тимощук // Вісник Національного університету «Львівська політехніка». Серія: Комп’ютерні системи та мережі. — Львів : Видавництво Львівської політехніки, 2017. — № 881. — С. 160–165.
dc.identifier.citationenTymoshchuk P. V. Parallel rank-order filtering based on impulse K-WINNERS-TAKE-ALL neural network / P. V. Tymoshchuk // Visnyk Natsionalnoho universytetu "Lvivska politekhnika". Serie: Kompiuterni systemy ta merezhi. — Lviv : Vydavnytstvo Lvivskoi politekhniky, 2017. — No 881. — P. 160–165.
dc.identifier.urihttps://ena.lpnu.ua/handle/ntb/42836
dc.language.isouk
dc.publisherВидавництво Львівської політехніки
dc.relation.ispartofВісник Національного університету «Львівська політехніка». Серія: Комп’ютерні системи та мережі, 881, 2017
dc.relation.references1. Majani E., Erlanson R., and Abu-Mostafa Y. On the k-winners-take-all network Ґ// in Advances in Neural Information Processing Systems 1, R. P. Lippmann, J. E. Moody, and D. S. Touretzky, Eds. San Mateo, CA: Morgan Kaufmann, 1989, pp. 634–642.
dc.relation.references2. Tymoshchuk P. A dynamic K-winners take all analog neural circuit // in Proc. IV th Int. Conf. “Perspective technologies and methods in MEMS design”, Lviv-Polyana, Ukraine, 2008, pp. 13–18.
dc.relation.references3. Wang J. Analysis and design of a k-winners-take-all network with a single state variable and the Heaviside step activation function // IEEE Trans. Neural Netw., vol. 21, no. 9, P. 1496–1506, Sept. 2010.
dc.relation.references4. Lippmann R. P. An introduction to computing with neural nets // IEEE Acoustics, Speech and Signal Processing Magazine, vol. 3, no. 4, pp. 4–22, Apr. 1987.
dc.relation.references5. Tymoshchuk P. and Kaszkurewicz E. A winner-take all circuit using neural networks as building blocks // Neurocomputing, vol. 64, pp. 375–396, Mar. 2005.
dc.relation.references6. Wunsch D. C. The cellular simultaneous recurrent network adaptive critic design for the generalized maze problem has a simple closed-form solution // in Proc. Int. Joint Conf. Neural Netw., Jul. 2000, P. 79–82.
dc.relation.references7. Atkins M. Sorting by Hopfield nets, in Proc. Int. Joint Conf. Neural Netw., Jun. 1989, – P. 65–68.
dc.relation.references8. Binh L. N. and Chong H. C. A neural-network contention controller for packet switching networks // IEEE Trans. Neural Netw. vol. 6, no. 6, P. 1402–1410, Nov. 1995.
dc.relation.references9. Itti L., Koch C., and Niebur E. A network of saliency-based visual attention for rapid scene analysis // IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 11, P. 1254 – 1259,Nov. 1998.
dc.relation.references10. Cilingiroglu U. and Dake T. L. E. Rank-order filter design with a sampled-analog multiplewinners-take-all core // IEEE J. Solid-State Circuits, vol. 37, no. 2, pp. 978-984, Aug. 2002.
dc.relation.references11. Erlanson R. and Abu-Mostafa Y. Analog neural networks as decoders // in Advances in Neural Information Processing Systems, vol. 1, R. P. Lippmann, J. E. Moody, and D. S. Touretzky, Eds. San Mateo, CA: Morgan Kaufmann, 1991.
dc.relation.references12. Fish A., Akselrod D., and 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, vol. 39, no. 3, P. 251–266, Jun. 2004.
dc.relation.references13. Jain B. J. and Wysotzki F. Central clustering of attributed graphs // Machine Learning, vol. 56, no. 1, pp. 169–207, Jul. 2004.
dc.relation.references14. Chartier S., Giguere G., Langlois D. and Sioufi R. Bidirectional associative memories, self-organizing maps and k-winners-take-all; uniting feature extraction and topological principles // in Proc. Int. Joint Conf. Neural Netw., Jun. 2009, pp. 503–510.
dc.relation.references15. G. N. DeSouza and A. C. Zak, “Vision for mobile robot navigation: a survey,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 2, р. 237–267, Feb. 2002.
dc.relation.references16. O’Reilly R. C. and Munakata Y. Computational Explorations in Cognitive Neuroscience: Understanding the Mind by Simulating the Brain. Cambridge, MA: MIT Press, 2000.
dc.relation.references17. Lazzaro J., Ryckebusch S., Mahowald M. A., and Mead C. A. Winner-take-all networks of O (N) complexity // in Advances in Neural Information Processing Systems 1, R. P. Lippmann, J. E. Moody, and D. S. Touretzky, Eds. San Mateo, CA: Morgan Kaufmann,1989, pp. 703-711.
dc.relation.references18. Sekerkiran B. and Cilingiroglu U. A CMOS K-winners-take-all circuits with 0(N) complexity // IEEE Trans. Circuits Syst. II, vol. 46, no. 1, р. 1–5, Jan. 1999.
dc.relation.references19. Maass W. Neural computation with winner-take-all as the only nonlinear operation // in Advances in Information Processing Systems, vol. 12, S. A. Solla, T. K. Leen, and K.-R. Mueller, Eds. Cambridge, MA: MIT Press, 2000, pp.293–299.
dc.relation.references20. Calvert B. D. and Marinov C. A. Another K-winners-take-all analog neural network // IEEE Trans. Neural Netw., vol. 4, no. 1, P. 829–838, Jul. 2000.
dc.relation.references21. Wang J. Analogue winner-take-all neural networks for determining maximum and minimum signals,” Int. J. Electron., vol. 77, no. 3, р. 355–367,Mar. 1994.
dc.relation.references22. Cichocki A. and Unbehauen R. Neural Networks for Optimization and Signal Processing. New York, NY, USA: Wiley, 1993.
dc.relation.referencesen1. Majani E., Erlanson R., and Abu-Mostafa Y. On the k-winners-take-all network G// in Advances in Neural Information Processing Systems 1, R. P. Lippmann, J. E. Moody, and D. S. Touretzky, Eds. San Mateo, CA: Morgan Kaufmann, 1989, pp. 634–642.
dc.relation.referencesen2. Tymoshchuk P. A dynamic K-winners take all analog neural circuit, in Proc. IV th Int. Conf. "Perspective technologies and methods in MEMS design", Lviv-Polyana, Ukraine, 2008, pp. 13–18.
dc.relation.referencesen3. Wang J. Analysis and design of a k-winners-take-all network with a single state variable and the Heaviside step activation function, IEEE Trans. Neural Netw., vol. 21, no. 9, P. 1496–1506, Sept. 2010.
dc.relation.referencesen4. Lippmann R. P. An introduction to computing with neural nets, IEEE Acoustics, Speech and Signal Processing Magazine, vol. 3, no. 4, pp. 4–22, Apr. 1987.
dc.relation.referencesen5. Tymoshchuk P. and Kaszkurewicz E. A winner-take all circuit using neural networks as building blocks, Neurocomputing, vol. 64, pp. 375–396, Mar. 2005.
dc.relation.referencesen6. Wunsch D. C. The cellular simultaneous recurrent network adaptive critic design for the generalized maze problem has a simple closed-form solution, in Proc. Int. Joint Conf. Neural Netw., Jul. 2000, P. 79–82.
dc.relation.referencesen7. Atkins M. Sorting by Hopfield nets, in Proc. Int. Joint Conf. Neural Netw., Jun. 1989, P. 65–68.
dc.relation.referencesen8. Binh L. N. and Chong H. C. A neural-network contention controller for packet switching networks, IEEE Trans. Neural Netw. vol. 6, no. 6, P. 1402–1410, Nov. 1995.
dc.relation.referencesen9. Itti L., Koch C., and Niebur E. A network of saliency-based visual attention for rapid scene analysis, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 11, P. 1254 – 1259,Nov. 1998.
dc.relation.referencesen10. Cilingiroglu U. and Dake T. L. E. Rank-order filter design with a sampled-analog multiplewinners-take-all core, IEEE J. Solid-State Circuits, vol. 37, no. 2, pp. 978-984, Aug. 2002.
dc.relation.referencesen11. Erlanson R. and Abu-Mostafa Y. Analog neural networks as decoders, in Advances in Neural Information Processing Systems, vol. 1, R. P. Lippmann, J. E. Moody, and D. S. Touretzky, Eds. San Mateo, CA: Morgan Kaufmann, 1991.
dc.relation.referencesen12. Fish A., Akselrod D., and 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, vol. 39, no. 3, P. 251–266, Jun. 2004.
dc.relation.referencesen13. Jain B. J. and Wysotzki F. Central clustering of attributed graphs, Machine Learning, vol. 56, no. 1, pp. 169–207, Jul. 2004.
dc.relation.referencesen14. Chartier S., Giguere G., Langlois D. and Sioufi R. Bidirectional associative memories, self-organizing maps and k-winners-take-all; uniting feature extraction and topological principles, in Proc. Int. Joint Conf. Neural Netw., Jun. 2009, pp. 503–510.
dc.relation.referencesen15. G. N. DeSouza and A. C. Zak, "Vision for mobile robot navigation: a survey," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 2, r. 237–267, Feb. 2002.
dc.relation.referencesen16. O’Reilly R. C. and Munakata Y. Computational Explorations in Cognitive Neuroscience: Understanding the Mind by Simulating the Brain. Cambridge, MA: MIT Press, 2000.
dc.relation.referencesen17. Lazzaro J., Ryckebusch S., Mahowald M. A., and Mead C. A. Winner-take-all networks of O (N) complexity, in Advances in Neural Information Processing Systems 1, R. P. Lippmann, J. E. Moody, and D. S. Touretzky, Eds. San Mateo, CA: Morgan Kaufmann,1989, pp. 703-711.
dc.relation.referencesen18. Sekerkiran B. and Cilingiroglu U. A CMOS K-winners-take-all circuits with 0(N) complexity, IEEE Trans. Circuits Syst. II, vol. 46, no. 1, r. 1–5, Jan. 1999.
dc.relation.referencesen19. Maass W. Neural computation with winner-take-all as the only nonlinear operation, in Advances in Information Processing Systems, vol. 12, S. A. Solla, T. K. Leen, and K.-R. Mueller, Eds. Cambridge, MA: MIT Press, 2000, pp.293–299.
dc.relation.referencesen20. Calvert B. D. and Marinov C. A. Another K-winners-take-all analog neural network, IEEE Trans. Neural Netw., vol. 4, no. 1, P. 829–838, Jul. 2000.
dc.relation.referencesen21. Wang J. Analogue winner-take-all neural networks for determining maximum and minimum signals," Int. J. Electron., vol. 77, no. 3, r. 355–367,Mar. 1994.
dc.relation.referencesen22. Cichocki A. and Unbehauen R. Neural Networks for Optimization and Signal Processing. New York, NY, USA: Wiley, 1993.
dc.rights.holder© Національний університет „Львівська політехніка“, 2017
dc.rights.holder© Тимощук П. В., 2017
dc.subjectмережа неперервного часу
dc.subjectнейронна мережа (НМ) типу “K-winners-take-all” (KWTA)
dc.subjectрівняння стану з розривною правою частиною
dc.subjectшлейф імпульсів
dc.subjectдельта-функція Дірака
dc.subjectпаралельне фільтрування рангу
dc.subjectcontinuous-time network
dc.subjectK-winners-take-all (KWTA) neural network (NN)
dc.subjectstate equation with a discontinuous right-hand side
dc.subjectimpulse train
dc.subjectDirac delta function
dc.subjectparallel rank-order filtering
dc.subject.udc004.032.026
dc.titleПаралельне фільтрування рангу на основі імпульсної нейронної мережі типу “K-WINNERS-TAKE-ALL”
dc.title.alternativeParallel rank-order filtering based on impulse K-WINNERS-TAKE-ALL neural network
dc.typeArticle

Files

Original bundle

Now showing 1 - 2 of 2
Thumbnail Image
Name:
2017n881_Tymoshchuk_P_V-Parallel_rank_order_160-165.pdf
Size:
564.47 KB
Format:
Adobe Portable Document Format
Thumbnail Image
Name:
2017n881_Tymoshchuk_P_V-Parallel_rank_order_160-165__COVER.png
Size:
364.41 KB
Format:
Portable Network Graphics

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.97 KB
Format:
Plain Text
Description: