logo

SCIENTIA SINICA Informationis, Volume 47 , Issue 9 : 1226-1241(2017) https://doi.org/10.1360/N112016-00266

A recurrent neural network based on memristive activation function and its associative memory

More info
  • ReceivedApr 16, 2017
  • AcceptedMay 23, 2017
  • PublishedSep 7, 2017

Abstract


Funded by

国家自然科学基金(61372139,61571372,61672436)

中央高校基本科研业务费专项资金(XDJK2016A001)


References

[1] Yang J, Wang L, Wang Y. A novel memristive Hopfield neural network with application in associative memory. Neurocomputing, 2017, 227: 142-148 CrossRef Google Scholar

[2] Huang Y J, Wang X Y, Long H X. Synthesization of high-capacity auto-associative memories using complex-valued neural networks. Chin Phys B, 2016, 25: 194--201. Google Scholar

[3] Hu X, Duan S, Chen G. Modeling affections with memristor-based associative memory neural networks. Neurocomputing, 2017, 223: 129-137 CrossRef Google Scholar

[4] Kumamoto T, Suzuki M, Matsueda H. Singular-value-decomposition analysis of associative memory in a neural network. J Phys Soc Japan, 2017, 86: 1--6. Google Scholar

[5] Zhou C, Zeng X, Yu J. A unified associative memory model based on external inputs of continuous recurrent neural networks. Neurocomputing, 2016, 186: 44-53 CrossRef Google Scholar

[6] Zhou C G, Zeng X Q, Jiang H B. A generalized bipolar auto-associative memory model based on discrete recurrent neural networks. Neurocomputing, 2015, 16: 201--208. Google Scholar

[7] Cao J, Zhou D. Stability analysis of delayed cellular neural networks. Neural Networks, 1998, 11: 1601-1605 CrossRef Google Scholar

[8] Zhigang Zeng , Jun Wang , Xiaoxin Liao . Global exponential stability of a general class of recurrent neural networks with time-varying delays. IEEE Trans Circuits Syst I, 2003, 50: 1353-1358 CrossRef Google Scholar

[9] Xiaofeng Liao , Guanrong Chen , Sanchez E N. LMI-based approach for asymptotically stability analysis of delayed neural networks. IEEE Trans Circuits Syst I, 2002, 49: 1033-1039 CrossRef Google Scholar

[10] Zhigang Zeng , Tingwen Huang , Wei Xing Zheng . Multistability of recurrent neural networks with time-varying delays and the piecewise linear activation function.. IEEE Trans Neural Netw, 2010, 21: 1371-1377 CrossRef PubMed Google Scholar

[11] Bao G, Zeng Z. Analysis and design of associative memories based on recurrent neural network with discontinuous activation functions. Neurocomputing, 2012, 77: 101-107 CrossRef Google Scholar

[12] Liu P, Zeng Z, Wang J. Complete stability of delayed recurrent neural networks with Gaussian activation functions.. Neural Networks, 2017, 85: 21-32 CrossRef PubMed Google Scholar

[13] Zhang F, Zeng Z. Multistability of recurrent neural networks with time-varying delays and nonincreasing activation function. Neurocomputing, 2016, 216: 135-142 CrossRef Google Scholar

[14] Misra J, Saha I. Artificial neural networks in hardware: A survey of two decades of progress. Neurocomputing, 2010, 74: 239-255 CrossRef Google Scholar

[15] Adhikari S P, Changju Yang S P, Hyongsuk Kim S P. Memristor bridge synapse-based neural network and its learning.. IEEE Trans Neural Netw Learning Syst, 2012, 23: 1426-1435 CrossRef PubMed Google Scholar

[16] Strukov D B, Snider G S, Stewart D R. The missing memristor found. Nature, 2008, 453: 80-83 CrossRef PubMed ADS Google Scholar

[17] Zha J X, Huang H, Liu Y J. A novel window function for memristor model with application in programming analog circuits. IEEE Trans Circ Syst-II, 2016, 63: 423--427. Google Scholar

[18] Wang L, Li H, Duan S. Pavlov associative memory in a memristive neural network and its circuit implementation. Neurocomputing, 2016, 171: 23-29 CrossRef Google Scholar

[19] Duan S, Zhang Y, Hu X. Memristor-based chaotic neural networks for associative memory. Neural Comput Applic, 2014, 25: 1437-1445 CrossRef Google Scholar

[20] Yang J J, Pickett M D, Li X. Memristive switching mechanism for metal/oxide/metal nanodevices.. Nat Nanotech, 2008, 3: 429-433 CrossRef PubMed Google Scholar

[21] Hu J, Wang J. Global uniform asymptotic stability of memristor-based recurrent neural networks with time delays. In: Proceedings of the 2010 International Joint Conference on Neural Networks, Barcelona, 2010. 1--8. Google Scholar

[22] Wang L D, Drakakis E M, Duan S K, et al. Memristor model and its application for chaos generation. Int J Bifurcat Chaos, 2012, 22: 1--14. Google Scholar