Abstract
In this paper, different chaos neurons are added in hidden layer of diagonal recurrent neural network. The advanced networks can solve the problem of long training time because of the convergence of chaos neuron. The Logistic map, the Chebyshev map, and the Sine map are used to construct networks. These networks are applied for image compression in order to compare their performance. The result of simulation test shows that the networks with chaos neurons are superior to traditional diagonal recurrent network in the effect of image reconstruction, and the networks with different chaotic maps are analyzed and compared for the first time.









Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Reza MS, Saeed F (2013) Bifurcations and chaos in a discrete-time-delayed Hopfield neural network with ring structures and different internal decays. Neurocomputing 99:154–162
Li J, Liu F, Guan HZ (2013) A new chaotic Hopfield neural network and its synthesis via parameter switchings. Neurocomputing 117:33–39
Kaslik E, Sivasundaram SS (2012) Nonlinear dynamics and chaos in fractional-order neural networks. Neural Netw 32:245–256
Zhang QH, Xie XP, Zhu P (2014) Sinusoidal modulation control method in a chaotic neural network. Commun Nonlinear Sci Numer Simulat 19:2793–2800
Günay E (2012) A new autonomous chaos generator from state controlled-cellular neural networks. Int J Bifurc Chaos 22(3):1250069
Rajan K, Abbott LF, Sompolinsky H (2010) Stimulus-dependent suppression of chaos in recurrent neural networks. Phys Rev E 82(1):011903
Huang WZ, Huang Y (2011) Chaos, bifurcation and robustness of a class of Hopfield neural networks. Int J Bifurc Chaos 21(3):885–895
Ahmed SU, Shahjahan M, Murase K (2011) Injecting chaos in feedforward neural networks. Neural Process Lett 34(1):87–100
Li Y, Zhua P, Xie XP (2012) Learning-induced pattern classification in a chaotic neural network. Phys Lett A 376:412–417
Ke Q, John OB (2014) Logistic Neural Networks: their chaotic and pattern recognition properties. Neurocomputing 125:184–194
Sun YB, Babovic V, Chan ES (2010) Multi-step-ahead model error prediction using time-delay neural networks combined with chaos theory. J Hydrol 395(1):109–116
Ghonaim W, Ghali NI, Hassanien AE (2013) An improvement of chaos-based hash function in cryptanalysis approach: an experience with chaotic neural networks and semi-collision attack. Memet Comput 5(3):179–185
Wang T, Wang KJ, Jia N (2012) Chaos control and associative memory of a time-delay globally coupled neural network using symmetric map. Commun Nonlinear Sci Numer Simulat 17:4731–4739
Zhao HQ, Zeng XP, Zhang JS (2011) A novel joint-processing adaptive nonlinear equalizer using a modular recurrent neural network for chaotic communication systems. Neural Netw 24(1):12–18
May RM (1976) Simple mathematical model with very complicated dynamics[J]. Nature 261:459–467
Lei LH, Ma GY, Cai XJ et al (2009) Study of chaotic sequence based on Chebyshev mapping[J]. Comput Eng 35(24):4–6
Chen Z, Tang TH (2010) Design and application of sine-map chaotic interleaver. Appl Res Comput 27(11):4276–4278
Acknowledgments
This research is supported by the science foundation of educational department of Hebei Province (Nos: QN2015125), the research and development program of science and technology of Shijiazhuang (Nos: 151790531A) and the National High Technology Research and Development Program of China (863 Program) (Nos: 2013AA014203).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Rights and permissions
About this article
Cite this article
Zhang, Y., Liu, M., Ma, B. et al. The performance evaluation of diagonal recurrent neural network with different chaos neurons. Neural Comput & Applic 28, 1611–1618 (2017). https://doi.org/10.1007/s00521-015-2129-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-015-2129-z