Abstract
Selecting the optimal topology of neural network for a particular application is a difficult task. In case of recurrent neural networks (RNN), most methods only introduce topologies in which their neurons are fully connected. However, recurrent neural network training algorithm has some drawbacks such as getting stuck in local minima, slow speed of convergence and network stagnancy. This paper propose an improved recurrent neural network trained with Cuckoo Search (CS) algorithm to achieve fast convergence and high accuracy. The performance of the proposed Cuckoo Search Recurrent Neural Network (CSRNN) algorithm is compared with Artificial Bee Colony (ABC) and similar hybrid variants. The simulation results show that the proposed CSRNN algorithm performs better than other algorithms used in this study in terms of convergence rate and accuracy.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Narendra KS, Parthasarathy K (1990) Identification and control of dynamic systems using neural networks. J IEEE Trans Neural Networks 1(1):4–27
Chen S, Billings SA (1992) Neural networks for nonlinear dynamics system modelling and identification. J Int J Control 56(2):319–346
Su HT, McAvoy TJ, Werbos P (1992) Long-term predictions of chemical processes using recurrent neural networks: a parallel training approach. J Ind Eng Chem Res 31(5):1338–1352
Mastorocostas PA, Theocharis JB (2006) A stable learning algorithm for block-diagonal recurrent neural networks: application to the analysis of lung sounds. J. IEEE Trans Syst Man Cybern B Cybern 36(2):242–254
Rehman MZ, Nawi NM, Ghazali MI (2012) Predicting noise-induced hearing loss (NIHL) and hearing deterioration index (HDI) in Malaysian industrial workers using GDAM algorithm. J Eng Technol (JET) 3(1):179–197 (UTeM)
Li CJ (1995) Mechanical system modelling using recurrent neural networks via quasi-Newton learning methods. J Appl Math Modell 19:420–428
Chan LW, Szeto CC (1999) Training recurrent neural network with block diagonal approximated Levenberg marquardt algorithm. In: IJCNN’99, vol 3. pp 1521–1526
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning internal representations by error propagation. In: Rumelhart DE, McClelland JL (eds) Parallel distributed processing: explorations in the microstructure of cognition, 45th edn. MIT Press, Cambridge
Warbos P (1993) The roots of backpropagation: from ordered derivatives to neural networks and political forecasting. Wiley, New York
Peng XG, Venayagamoorthy K, Corzin KA (2007) Combined training of recurrent neural networks with particle swarm optimization and backpropagation algorithms for impedance identification. In: Proceedings of the 2007 IEEE swarm intelligence symposium, pp 9–15
Juang CF (2004) A hybrid of genetic algorithm and particleswarm optimization for recurrent network design. J IEEE Trans Syst Man Cybern 34(2):997–1006
Yang XS, Deb S (2009) Cuckoo search via Lévy flights. In: Proceedings of world congress on nature and biologically inspired computing, India, pp 210–214
Yang XS, Deb S (2010) Engineering optimisation by cuckoo search. J Int J Math Modell Numer Optim 1(4):330–343
Tuba M, Subotic M, Stanarevic N (2011) Modified cuckoo search algorithm for unconstrained optimization problems. In: Proceedings of the European computing conference (ECC’11), pp 263–268
Tuba M, Subotic M, Stanarevic N (2012) Performance of a modified cuckoo search algorithm for unconstrained optimization problems faculty of computer science faculty of computer. Science 11(2):62–74
Yang XS, Deb S (2010) Engineering optimisation by cuckoo search. J Int J Math Modell Numer Optim 1(4):330–343
Chaowanawate K, Heednacram A (2012) Implementation of cuckoo search in RBF neural network for flood forecasting. In: Proceedings of 2012 fourth international conference on computational intelligence, communication systems and networks, pp 22–26
Elman JL (1990) Finding structure in time. J Cognitive Sci 14:179–211
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media Singapore
About this paper
Cite this paper
Nawi, N.M., Khan, A., Rehman, M.Z. (2014). A New Optimized Cuckoo Search Recurrent Neural Network (CSRNN) Algorithm. In: Mat Sakim, H., Mustaffa, M. (eds) The 8th International Conference on Robotic, Vision, Signal Processing & Power Applications. Lecture Notes in Electrical Engineering, vol 291. Springer, Singapore. https://doi.org/10.1007/978-981-4585-42-2_39
Download citation
DOI: https://doi.org/10.1007/978-981-4585-42-2_39
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-4585-41-5
Online ISBN: 978-981-4585-42-2
eBook Packages: EngineeringEngineering (R0)