Abstract
This paper presents a novel neural network model with hybrid quantized architecture to improve the performance of the conventional Elman networks. The quantum gate technique is introduced for solving the pattern mismatch between the inputs stream and one-time-delay state feedback. A quantized back-propagation training algorithm with an adaptive dead zone scheme is developed for providing an optimal or suboptimal tradeoff between the convergence speed and the generalization performance. Furthermore, the effectiveness of the new real time learning algorithm is demonstrated by proving the quantum gate parameter convergence based on Lyapunov method. The numerical experiments are carried out to demonstrate the accuracy of the theoretical results.
Similar content being viewed by others
References
Elman JL (1990) Finding structure in time. Cogn Sci 14: 179–211
Jordan M (1986) Serial order: a parallel distributed processing approach. ICS Report 8604, Institute of Cognitive Science, University of California San Diego, San Diego
Lee SW, Song HH (1997) New recurrent neural network architecture for visual pattern recognition. IEEE Trans Neural Netw 8(2): 331–340
Goh WY, Lim CP, Peh KK (2003) Predicting drug dissolution profiles with an ensemble of boosted neural networks: a time series approach. IEEE Trans Neural Netw 14(2): 459–463
Toqeer RS, Bayindir NS (2003) Speed estimation of an induction motor using Elman neural network. Neurocomputing 55(3–4): 727–730
Valle-Lisboa JC, Reali F, Anastasa H (2005) Elman topology with sigma–pi units: an application to the modeling of verbal hallucinations in schizophrenia. Neural Netw 18(7): 863–877
Liou C, Huang J, Yang W (2008) Modeling word perception using the Elman network. Neurocomputing 71(16–18): 3150–3157
Ardalani-Farsa M, Zolfaghari S (2010) Chaotic time series prediction with residual analysis method using hybrid Elman–NARX neural networks. Neurocomputing 73(13–15): 2540–2553
Song Q, Wu Y, Soh YC (2008) Robust adaptive gradient-descent training algorithm for recurrent neural networks in discrete time domain. IEEE Trans Neural Netw 19(11): 1841–1853
Kremer SC (1995) On the computational power of Elman-style recurrent networks. IEEE Trans Neural Netw 6(4): 1000–1004
Wang D, Liu X, Ahalt SC (1996) On temporal generalization of simple recurrent networks. Neural Netw 9(7): 1099–1118
Li X, Chen G, Chen Z, Yuan Z (2002) Chaotifying linear Elman networks. IEEE Trans Neural Netw 13(5): 1193–1199
Deutsch D, Jozsa R (1992) Rapid solution of problems by quantum computation. Proc Math Phys Sci A 439: 553–558
Ventura D, Martinez T (2000) Quantum associative memory. Inf Sci 124(1): 273–296
Menneer T, Narayanan A (1995) Quantum-inspired neural networks. Technical Report R329, University of Exeter, Exeter
Kouda N, Matsui N, Nishimura H (2001) Image compression by layered quantum neural networks. Neural Process Lett 16(1): 67–80
Kouda N, Matsui N, Nishimura H, Peper F (2005) An examination of qubit neural network in controlling an inverted pendulum. Neural Process Lett 22: 277–290
Gopathy P, Nicolaos BK (1997) Quantum neural networks (QNN’s): inherently fuzzy feedforward neural networks. IEEE Trans Neural Netw 8(3): 679–693
Matsui N, Takai M, Nishimura H (1988) A network model based on qubit-like neuron corresponding to quantum circuit. IEICE J81-A(12):1687–1692
Luitel B, Venayagamoorthy GK (2010) Quantum inspired PSO for the optimization of simultaneous recurrent neural networks as MIMO learning systems. Neural Netw 23: 583–586
Li PH, Chai Y, Xiong QY (2011) Quantized neuronal modeling: quantum gate structure in Elman networks. In: Proceedings of fourth international workshop on advanced computational intelligence. IEEE Press, Wu Han, pp 315–320
Song Q (2010) On the weight convergence of Elman networks. IEEE Trans Neural Netw 21(3): 463–480
Vidyasagar M (1980) Nonlinear systems analysis. Prentice-Hall, Englewood Cliffs
Hammer B, Tino P (2003) Recurrent neural networks with small weights implement definite memory machines. Neurocomputing 15: 1897–1929
Song Q, Spall J, Soh YC, Ni J (2008) Robust neural network tracking controller using simultaneous perturbation stochastic approximation. IEEE Trans Neural Netw 19(5): 817–835
Phat VN, Botmart T, Niamsupb P (2008) Switching design for exponential stability of a class of nonlinear hybrid time-delay systems. Nonlinear Anal Hybrid Syst 3: 1–10
Phat VN, Niamsupb P (2010) A novel exponential stability condition of hybrid neural networks with time-varying delay. Vietnam J Math 38: 341–351
Zames G (1966) On the input–output stability of time-varying nonlinear feedback systems, part I. IEEE Trans Autom Control 11(2): 228–238
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Li, P., Chai, Y. & Xiong, Q. Quantized Neural Modeling: Hybrid Quantized Architecture in Elman Networks. Neural Process Lett 37, 163–187 (2013). https://doi.org/10.1007/s11063-012-9240-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-012-9240-2