Analysis and design of winner-take-all behavior based on a novel memristive neural network

详细信息    查看全文

• 作者：Ailong Wu (1) (2) (3)
  Zhigang Zeng (3) (4)
  Jiejie Chen (3) (4)
  
• 关键词：Winner ; take ; all ; Memristive neural networks ; Hybrid systems
• 刊名：Neural Computing & Applications
• 出版年：2014
• 出版时间：June 2014
• 年：2014
• 卷：24
• 期：7-8
• 页码：1595-1600
• 全文大小：
• 参考文献：1. Burwick T (2009) On the relevance of local synchronization for establishing a winner-take-all functionality of the gamma cycle. Neurocomputing 72(7鈥?):1525鈥?533 CrossRef
  2. Cai XD, Prokhorov DV, Wunsch DC (2007) Training winner-take-all simultaneous recurrent neural networks. IEEE Trans Neural Netw 18(3):674鈥?84 CrossRef
  3. Costea RL, Marinov CA (2011) New accurate and flexible design procedure for a stable KWTA continuous time network. IEEE Trans Neural Netw 22(9):1357鈥?367 CrossRef
  4. Fang YG, Cohen MA, Kincaid TG (2010) Dynamic analysis of a general class of winner-take-all competitive neural networks. IEEE Trans Neural Netw 21(5):771鈥?83 CrossRef
  5. Mao ZH, Massaquoi SG (2007) Dynamics of winner-take-all competition in recurrent neural networks with lateral inhibition. IEEE Trans Neural Netw 18(1):55鈥?9 CrossRef
  6. Qu H, Yi Z, Wang XB (2009) A winner-take-all neural networks of / N linear threshold neurons without self-excitatory connections. Neural Process Lett 29(3):143鈥?54 CrossRef
  7. Hafliger P (2007) Adaptive WTA with an analog VLSI neuromorphic learning chip. IEEE Trans Neural Netw 18(2):551鈥?72 CrossRef
  8. Marinov CA, Costea RL (2010) Time-oriented synthesis for a WTA continuous-time neural network affected by capacitive cross-coupling. IEEE Trans Circuits Syst I Reg Pap 57(6):1358鈥?370 CrossRef
  9. Oster M, Wang YX, Douglas R, Liu SC (2008) Quantification of a spike-based winner-take-all VLSI network. IEEE Trans Circuits Syst I Reg Pap 55(10):3160鈥?169 CrossRef
  10. Hu XL, Wang J (2008) An improved dual neural network for solving a class of quadratic programming problems and its k-winners-take-all application. IEEE Trans Neural Netw 19(12):2022鈥?031 CrossRef
  11. Liu SB, Wang J (2006) A simplified dual neural network for quadratic programming with its KWTA application. IEEE Trans Neural Netw 17(6):1500鈥?510 CrossRef
  12. Liu QS, Wang J (2008) Two k-winners-take-all networks with discontinuous activation functions. Neural Netw 21(2鈥?):406鈥?13
  13. Wang J (2010) Analysis and design of a k-winners-take-all model with a single state variable and Heaviside step activation function. IEEE Trans Neural Netw 21(9):1496鈥?506 CrossRef
  14. Cantley KD, Subramaniam A, Stiegler HJ, Chapman RA, Vogel EM (2011) Hebbian learning in spiking neural networks with nanocrystalline silicon TFTs and memristive synapses. IEEE Trans Nanotechnol 10(5):1066鈥?073 CrossRef
  15. Cantley KD, Subramaniam A, Stiegler HJ, Chapman RA, Vogel EM (2012) Neural learning crcuits utilizing nano-crystalline silicon transistors and memristors. IEEE Trans Neural Netw Learn Syst 23(4):565鈥?73 CrossRef
  16. Itoh M, Chua LO (2009) Memristor cellular automata and memristor discrete-time cellular neural networks. Int J Bifurcat Chaos 19(11):3605鈥?656 CrossRef
  17. Kim H, Sah MP, Yang CJ, Roska T, Chua LO (2012) Neural synaptic weighting with a pulse-based memristor circuit. IEEE Trans Circuits Syst I Reg Pap 59(1):148鈥?58 CrossRef
  18. Pershin YV, Di Ventra M (2010) Experimental demonstration of associative memory with memristive neural networks. Neural Netw 23(7):881鈥?86 CrossRef
  19. Wen SP, Zeng ZG (2012) Dynamics analysis of a class of memristor-based recurrent networks with time-varying delays in the presence of strong external stimuli. Neural Process Lett 35(1):47鈥?9 CrossRef
  20. Wu AL, Zeng ZG (2012) Exponential stabilization of memristive neural networks with time delays. IEEE Trans Neural Netw Learn Syst 23(12):1919鈥?929 CrossRef
  21. Wu AL, Zeng ZG (2012) Dynamic behaviors of memristor-based recurrent neural networks with time-varying delays. Neural Netw 36:1鈥?0 CrossRef
  22. Huang TW, Li CD, Duan SK, Starzyk JA (2012) Robust exponential stability of uncertain delayed neural networks with stochastic perturbation and impulse effects. IEEE Trans Neural Netw Learn Syst 23(6):866鈥?75 CrossRef
  23. Huang TW (2011) Robust stability of delayed fuzzy Cohen-Grossberg neural networks. Comput Math Appl 61(8):2247鈥?250 CrossRef
  24. Zhang HG, Wang YC (2008) Stability analysis of Markovian jumping stochastic Cohen-Grossberg neural networks with mixed time delays. IEEE Trans Neural Netw 19(2):366鈥?70 CrossRef
  25. Zhang HG, Liu JH, Ma DZ, Wang ZS (2011) Data-core-based fuzzy min-max neural network for pattern classification. IEEE Trans Neural Netw 22(12):2339鈥?352 CrossRef
  26. Zhang HG, Ma TD, Huang GB, Wang ZL (2010) Robust global exponential synchronization of uncertain chaotic delayed neural networks via dual-stage impulsive control. IEEE Trans Syst Man Cybern B Cybern 40(3):831鈥?44 CrossRef
  27. Yu W (2009) A novel fuzzy-neural-network modeling approach to crude-oil blending. IEEE Trans Control Syst Technol 17(6):1424鈥?431 CrossRef
  28. Yu W, Li XO (2010) Automated nonlinear system modeling with multiple fuzzy neural networks and kernel smoothing. Int J Neural Syst 20(5):429鈥?35 CrossRef
  29. Shen Y, Wang J (2009) Almost sure exponential stability of recurrent neural networks with Markovian switching. IEEE Trans Neural Netw 20(5):840鈥?55 CrossRef
  30. Shen Y, Wang J (2012) Robustness analysis of global exponential stability of recurrent neural networks in the presence of time delays and random disturbances. IEEE Trans Neural Netw Learn Syst 23(1):87鈥?6 CrossRef
  
• 作者单位：Ailong Wu (1) (2) (3)
  Zhigang Zeng (3) (4)
  Jiejie Chen (3) (4)
  
  1. College of Mathematics and Statistics, Hubei Normal University, Huangshi, 435002, China
  2. Institute for Information and System Science, Xi鈥檃n Jiaotong University, Xi鈥檃n, 710049, China
  3. School of Automation, Huazhong University of Science and Technology, Wuhan, 430074, China
  4. Key Laboratory of Image Processing and Intelligent, Control of Education Ministry of China, Wuhan, 430074, China
  
• ISSN：1433-3058

文摘

In this paper, some sufficient conditions are derived to guarantee a novel memristive neural network for realizing winner-take-all behavior. Some design methods for synthesizing the winner-take-all behavior based on the memristive neural network are developed by using the obtained results. Finally, simulation results demonstrate the validity and characteristics of the proposed approach.