Effects of connectivity structure of complex echo state network on its prediction performance for nonlinear time series

Neurocomputing

Volumn 73, Issue 10-12, 2010, Pages 2177-2185

  Song, Qingsong ^a   Feng, Zuren ^a  

^a XI'AN JIAOTONG UNIVERSITY   (China)

Author keywords

Chaotic time series prediction; Complex network; Complexity; Connectivity structure; Echo state network

Indexed keywords

CHAOTIC TIME SERIES PREDICTION; COMPLEX NETWORKS; CONNECTIVITY INDICES; CONNECTIVITY STRUCTURES; CONSTRUCTION PROCESS; ECHO STATE NETWORKS; GROWTH FACTOR; NONLINEAR TIME SERIES; OPTIMAL PERFORMANCE; PERFORMANCE PREDICTOR; PREDICTION PERFORMANCE; RESERVOIR COMPUTING;

BIOACTIVITY; CIRCUIT THEORY; PEPTIDES; TIME SERIES;

FORECASTING;

GROWTH FACTOR;

ARTICLE; COMPLEX ECHO STATE NETWORK; COMPUTER NETWORK; COMPUTER PREDICTION; MATHEMATICAL COMPUTING; NERVE CELL NETWORK; NONLINEAR SYSTEM; PERFORMANCE MEASUREMENT SYSTEM; PRIORITY JOURNAL; PROCESS OPTIMIZATION; QUANTITATIVE ANALYSIS; TIME SERIES ANALYSIS;

EID: 77952551014     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2010.01.015     Document Type: Article

References (31)

1. Buonomano D.V., Merzenich M.M. Temporal information transformed into a spatial code by a neural network with realistic properties. Science 1995, 267:1028-1030.
2. K. Bush, B. Tsendjav, Improving the richness of echo state features using next ascent local search, in: Proceedings of Artificial Neural Networks in Engineering Conference, 2005, pp. 227-232.
3. Chen Y., Yang B., Dong J., Abraham A. Time-series forecasting using flexible neural tree model. Information Sciences 2005, 174:219-235.
4. Dominey P.F. Complex sensory-motor sequence learning based on recurrent state representation and reinforcement learning. Biological Cybernetics 1995, 73:265-274.
5. Haeusler S., Maass W. A statistical analysis of information-processing properties of lamina-specific cortical microcircuit models. Cerebral Cortex 2007, 17:149-162.
6. M.A. Hajnal, A. Lorincz, Critical echo state networks, in: Proceedings of ICANN 2006, Part I, Lecture Notes in Computer Science, vol. 4131, 2006, pp. 658-667.
7. Haykin S. Neural Networks: A Comprehensive Foundation 1998, Prentice-Hall, New Jersey.
8. Hilgetag C.C., Kaiser M. Clustered organization of cortical connectivity. Neuroinformatics 2004, 2:353-360.
9. H. Jaeger, The echo state approach to analyzing and training recurrent neural networks, Technical Report No. 148, German National Research Center for Information Technology, Bremen, 2001.
10. H. Jaeger, Tutorial on training recurrent neural networks, covering BPTT, RTRL, EKF and the "echo state network" approach, Technical Report No. 159, German National Research Center for Information Technology, Bremen, 2002.
11. Jaeger H., Haass H. Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 2004, 304:78-80.
12. Jaeger H., Lukoševičius M., Popovici D., Siewert U. Optimization and applications of echo state networks with leaky-integrator neurons. Neural Networks 2007, 20:335-352.
13. Kaiser M., Hilgetag C.C. Modeling the development of cortical systems networks. Neurocomputing 2004, 58-60:297-302.
14. Kaiser M., Hilgetag C.C. Development of multi-cluster cortical networks by time windows for spatial growth. Neurocomputing 2007, 70:1829-1832.
15. B. Liebald, Exploration of effects of different network topologies on the ESN signal crosscorrelation matrix spectrum, B.Sc. Thesis, School of Engineering and Science, International University Bremen, 2004.
16. M. Lukosevicius, Echo state networks with trained feedbacks, Technical Report No. 4, School of Engineering and Science, Jacobs University Bremen, 2007.
17. Maass W., Natschlager T., Markram H. Real-time computing without stable states: a new framework for neural computation based on perturbation. Neural Computation 2002, 14:2531-2560.
18. Newman M.E.J. The structure and function of complex networks. SIAM Review 2003, 45:167-256.
19. Nisbach F., Kaiser M. Developmental time windows for spatial growth generate multiple-cluster small-world networks. The European Physical Journal B 2007, 58:185-191.
20. Ozturk M.C., Xu D., Principe J.C. Analysis and design of echo state networks. Neural Computation 2007, 19:111-138.
21. D. Prokhorov, Echo state networks: appeal and challenges, in: Proceedings of International Joint Conference on Neural Networks, vol. 2, 2005, pp. 1463-1466.
22. M. Salmen, P.G. Ploger, Echo state networks used for motor control, in: Proceedings of the 2005 IEEE International Conference on Robotics and Automation, 2005, pp. 1953-1958.
23. Skowronski M.D., Harris J.G. Noise-robust automatic speech recognition using a predictive echo state network. IEEE Transactions on Audio, Speech, and Language Processing 2007, 15:1724-1730.
24. Stancak J.A., Wackermann J. Spatial EEG synchronization over sensorimotor hand areas in brisk and slow self-paced index finger movements. Brain Topography 1998, 11:23-30.
25. Steil J.J. Online stability of backpropagation-decorrelation recurrent learning. Neurocomputing 2006, 69:642-650.
26. J.J. Steil, Several ways to solve the MSO problems, in: Proceedings-European Symposium on Artificial Neural Networks, 2007, pp. 489-494.
27. Verstraeten D., Schrauwen B., Haene M.D., Stroobandt D. An experimental unification of reservoir computing methods. Neural Networks 2007, 20:391-403.
28. Wackermann J. Towards a quantitative characterization of functional states of the brain: from the non-linear methodology to the global linear description. International Journal of Psychophysiology 1999, 34:65-80.
29. Wiener N. Cybernetics 1965, The MIT Press.
30. F. Wyffels, B. Schrauwen, D. Stroobandt, Stable output feedback in reservoir computing using ridge regression, in: Proceedings of the 18th ICANN, Part I, Lecture Notes in Computer Science, vol. 5163, 2008, pp. 808-817.
31. Xue Y., Yang L., Haykin S. Decoupled echo state networks with lateral inhibition. Neural Networks 2007, 20:365-376.