SEMI-SUPERVISED NEURAL CLASSIFIER USING MEMRISTIVE NANODEVICES

Ahmad Muqeem Sheri, Seungjong No, Moongu Jeon

References

  1. [1] G. Cybenko, “Approximation by superpositions of asigmoidal function,” Mathematics Of Control SignalsAnd Systems, vol. 2, no. 4, pp. 303–314, 1989.
  2. [2] Y. Liao, “Neural networks in hardware: A survey,”Department of Computer Science, University of Cali-fornia, 2001.
  3. [3] D. A. Drachman, “Do we have brain to spare?,” Neu-rology, vol. 64, pp. 2004–5, June 2005.
  4. [4] G. Snider, “Cortical computing with memristive nan-odevices,” SciDAC Review, pp. 58–65, 2008.
  5. [5] N. Rougier and Y. Boniface, “Dynamic self-organising map,” Neurocomputing, vol. 74, pp. 1840–1847, May 2011.
  6. [6] D. B. Strukov, G. S. Snider, D. R. Stewart, and R. S.Williams, “The missing memristor found.,” Nature,vol. 453, pp. 80–3, May 2008.
  7. [7] A. Radwan and M. Zidan, “On the mathematicalmodeling of memristors,” International Conferenceon, vol. 2, no. Icm, pp. 9–12, 2010.
  8. [8] G. S. Snider, “Self-organized computation with un-reliable, memristive nanodevices,” Nanotechnology,vol. 18, p. 365202, Sept. 2007.
  9. [9] S. H. Jo, K.-H. Kim, and W. Lu, “High-density cross-bar arrays based on a Si memristive system.,” Nanoletters, vol. 9, pp. 870–4, Feb. 2009.
  10. [10] W. V. William H. Press, Saul Teukolsky and B. Flan-nery, Numerical Recipes. Cambridge UniversityPress, 1986.
  11. [11] C. Gear, “Telescopic projective methods for stiff dif-ferential equations,” J. Comp. Phys, 2003.

Important Links:

Go Back