Abstract
The Monte Carlo adaptation rule has been proposed to design asymmetric neural network. By adjusting the degree of the symmetry of the networks designed by this rule, the spurious memories or unwanted attractors of the networks can be suppressed completely. We have extended this rule to design full-connected neural networks and diluted neural networks. Comparing the dynamics of these two neural networks, the simulation results indicated that the performance of diluted neural network was poorer than the performance of full-connected neural network. As to this point, further research is needed. In this paper, we use the annealed dilution method to design a diluted neural network with fixed degree of dilution. By analyzing the dynamics of the diluted neural network, it is verified that asymmetric full-connected neural network do have significant advantages over the asymmetric diluted neural network.
Article PDF
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
J.J.Hopfield, Neural networks and physical systems with emergent collective computational abilities, Proceedings of the National Academy of Sciences of the United States of America 79 (8) (1982) 2554–2558.
S.Hu, X.Liao, X.Mao, Stochastic hopfield neural networks, Journal of Physics A: Mathematical and General 36 (9) (2003) 2235–2249.
G.Huang, J.Cao, Multistability in bidirectional associative memory neural networks, Physics Letters A 372 (16) (2008) 2842–2854.
T.Isokawa, H.Nishimura, N.Kamiura, N.Matsui, Associative memory in quaternionic hopfield neural network, International Journal of Neural Systems 18 (2) (2008) 135–145.
A.Singh, S.Kumar, T.P.Singh, Analysis of hopfield associative memory with combination of mc adaptation rule and an evolutionary algorithm, International Journal of Computer Applications 78 (11) (2013) 37–42.
T.P.Vogels, K.Rajan, L.F.Abbott, Neural network dynamics, Annual Review of Neuroscience 28 (2005) 357–376.
F.Yasar, The investigation of the spin glass properties of the hopfield neural network model, International Journal of Modern Physics C 16 (3) (2005) 427–437.
H.Zhao, General vector machine, http://arxiv.org/abs/1602.03950 (2016).
M.Gao, B.Cui, Adaptive synchronization in an array of asymmetric coupled neural networks, Chinese Physics B 18 (1) (2009) 76–83.
T.Jin, H.Zhao, Pattern recognition using asymmetric attractor neural networks, Physical Review E 72 (6) (2005) 06611:1–7.
J.Lu, D.W.C.Ho, M.Liu, Globally exponential synchronization in an array of asymmetric coupled neural networks, Physics Letters A 369 (5–6) (2007) 444–451.
H.Soula, G.Beslon, O.Mazet, Spontaneous dynamics of symmetric random recurrent spiking neural networks, Neural Computation 18 (1) (2006) 60–79.
P.Zheng, W.Tang, J.Zhang, Efficient continuous-time asymmetric hopfield networks for memory retrieval, Neural Computation 22 (6) (2010) 1597–1614.
H.Zhao, Designing asymmetric neural networks with associative memory, Physical Review E 70 (6) (2004) 066137:1–4.
L.Wang, Q.Zhou, T.Jin, H.Zhao, Feed-back neural networks with discrete weights, Neural Computing and Application 22 (6) (2013) 1063–1069.
J.W.Bohland, A. Minai, Efficient associative memory using small-world architecture, Neurocomputing 38–40 (2001) 489–496.
N. Davey, R. Adams, High capacity associative memories and connection constraints, Connection Science 16 (1) (2004) 47–65.
A. Sankar, R. Mammone, Optimal pruning of neural tree networks for improved generalization, in: IEEE International Joint Conference on Neural Networks, 1991, pp. 219–224.
F.Liu, M.Er, A novel efficient learning algorithm for self-generating fuzzy neural network with applications, International Journal of Neural Systems 22 (1) (2012) 21–35.
C.Palm, Neural associative memories and sparse coding, Neural Networks 37 (1) (2013) 165–171.
H. Q. Zhao, S. B. Gao, Z. Y. He, X. P. Zeng, W. D. Jin, T. R. Li, Identification of nonlinear dynamic system using a novel recurrent wavelet neural network based on the pipelined architecture, IEEE Transactions on Industrial Electronics 61 (8) (2014) 4171–4182.
H. Q. Zhao, J. S. Zhang, Adaptively combined fir and functional link artificial neural network equalizer for nonlinear communication channel, IEEE Transactions on Neural Networks 20 (4) (2009) 665–674.
H. Q. Zhao, X. P. Zeng, Z. Y. He, Low-complexity nonlinear adaptive filter based on a pipelined bilinear recurrent neural network, IEEE Transactions on Neural Networks 22 (9) (2011) 1494–1507.
H. Q. Zhao, X. P. Zeng, Z. Y. He, W. D. Jin, T. R. Li, Complex-valued pipelined decision feedback recurrent neural network for non-linear channel equalisation, IET Communications 6 (9) (2012) 1082–1096.
H. Q. Zhao, X. P. Zeng, J. S. Zhang, R. Tian, Y. G. Liu, D. Ruan, Pipelined functional link artificial recurrent neural network with the decision feedback structure for nonlinear channel equalization, Information Sciences 181 (17) (2011) 3677–3692.
M.Bouten, Storage capacity of diluted neural networks, Lecture Notes in Physics 368 (1990) 225–236.
T.Hastie, R.Tibshirani, J.Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer, 2009.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
About this article
Cite this article
Wang, L., Shen, J., Zhou, Q. et al. An Evaluation of the Dynamics of Diluted Neural Network. Int J Comput Intell Syst 9, 1191–1199 (2016). https://doi.org/10.1080/18756891.2016.1256578
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1080/18756891.2016.1256578