Partially connected feedforward neural networks on Apollonian networks

Physica A: Statistical Mechanics and its Applications

Volumn 389, Issue 22, 2010, Pages 5298-5307

  Wong, W K ^a   Guo, Z X ^a   Leung, S Y S ^a  

^a HONG KONG POLYTECHNIC UNIVERSITY   (Hong Kong)

Author keywords

Apollonian networks; Feedforward neural networks; Partially connected neural networks; Randomly connected neural networks

Indexed keywords

LEARNING ALGORITHMS;

APOLLONIAN NETWORKS; FUNCTION APPROXIMATION; GENERALIZATION PERFORMANCE; INPUT AND OUTPUTS; PARTIALLY CONNECTED NEURAL NETWORK; TRAINING SPEED;

FEEDFORWARD NEURAL NETWORKS;

EID: 77956949923     PISSN: 03784371     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.physa.2010.06.061     Document Type: Article

References (40)

1. M. Paliwal, and U. Kumar Neural networks and statistical techniques: a review of applications Expert Syst. Appl. 36 January 2009 2 17
2. A. Vellido, P. Lisboa, and J. Vaughan Neural networks in business: a survey of applications (19921998) Expert Syst. Appl. 17 July 1999 51 70
3. Y. Chang, and H. Yen Adaptive output feedback tracking control for a class of uncertain nonlinear systems using neural networks IEEE Trans. Syst. Man Cybern. B 35 December 2005 1311 1316
4. J.L. Noyes Neural network training E. Fiesler, R. Beale, Handbook of Neural Computation 1997 Oxford University Press Oxford, UK pp. B3.5:1-6
5. L. Holmstrom, and P. Koistinen Using additive noise in back-propagation training IEEE Trans. Neural Netw. 3 January 1992 24 38
6. C. Wang, and J. Principe Training neural networks with additive noise in the desired signal IEEE Trans. Neural Netw. 10 November 1999 1511 1517
7. S. Amari, N. Murata, K. Muller, M. Finke, and H. Yang Asymptotic statistical theory of overtraining and cross-validation IEEE Trans. Neural Netw. 8 September 1997 985 996
8. L. Prechelt Automatic early stopping using cross validation: quantifying the criteria Neural Netw. 11 June 1998 761 767
9. R. Setiono Feedforward neural network construction using cross validation Neural Comput. 13 December 2001 2865 2877
10. I.V. Tetko, D.J. Livingstone, and A.I. Luik Neural-network studies. 1. Comparison of overfitting and overtraining J. Chem. Inf. Comput. Sci. 35 SeptemberOctober 1995 826 833
11. Y. Liu, and X. Yao Simultaneous training of negatively correlated neural networks in an ensemble IEEE Trans. Syst. Man Cybern. B 29 December 1999 716 725
12. M. Islam, M. Sattar, M. Amin, X. Yao, and K. Murase A new adaptive merging and growing algorithm for designing artificial neural networks IEEE Trans. Syst. Man Cybern. B 39 June 2009 705 722
13. M. Islam, M. Sattar, M. Amin, X. Yao, and K. Murase A new constructive algorithm for architectural and functional adaptation of artificial neural networks IEEE Trans. Syst. Man Cybern. B 39 2009 1590 1605
14. D. Elizondo, and E. Fiesler A surbey of partially connected neural networkds Int. J. Neural Syst. 8 OctoberDecember 1997 535 558
15. J. Torres, M. Munoz, J. Marro, and P. Garrido Influence of topology on the performance of a neural network Neurocomputing 5860 June 2004 229 234
16. A. Rajapakse, K. Furuta, and S. Kondo Identification of nonlinear dynamic models with partially connected neural networks trained using orthogonal least square estimation Trans. IEEJ-Part C 119-C March 1999 335 343
17. G. Wyeth, G. Buskey, J. Roberts, Flight control using an artificial neural network, in: Proc. of the Australian Conf. on Robot. and Automat., ACRA'00, 2000, pp. 6570.
18. S. Kang, and C. Isik Partially connected feedforward neural networks structured by input types IEEE Trans. Neural Netw. 16 January 2005 175 184
19. D. Bassett, and E. Bullmore Small-world brain networks Neuroscientist 12 December 2006 512 523
20. O. Sporns, and C.J. Honey Small worlds inside big brains Proc. Natl. Acad. Sci. USA 103 December 2006 19219 19220
21. D. Watts, and S. Strogatz Collective dynamics of 'small-world' networks Nature 393 June 1998 440 442
22. S. Sakata, and T. Yamamori Topological relationships between brain and social networks Neural Netw. 20 January 2007 12 21
23. V. Eguiluz, D. Chialvo, G. Cecchi, M. Baliki, and A. Apkarian Scale-free brain functional networks Phys. Rev. Lett. 94 January 2005 018102:1-4
24. M. Kaiser, R. Martin, P. Andras, and M. Young Simulation of robustness against lesions of cortical networks Eur. J. Neurosci. 25 May 2007 3185 3192
25. Z. Deng, and Y. Zhang Collective behavior of a small-world recurrent neural system with scale-free distribution IEEE Trans. Neural Netw. 18 September 2007 1364 1375
26. S. Lu, J. Fang, A. Guo, and Y. Peng Impact of network topology on decision-making Neural Netw. 22 January 2009 30 40
27. D. Simard, L. Nadeau, and H. Kroger Fastest learning in small-world neural networks Phys. Lett. A 336 February 28 2005 8 15
28. L. de Arcangelis, and H. Herrmann Learning as a phenomenon occurring in a critical state Proc. Natl. Acad. Sci. USA 107 March 2 2010 3977 3981
29. D. Stauffer, A. Aharony, L. Costa, and J. Adler Efficient Hopfield pattern recognition on a scale-free neural network Eur. Phys. J. B 32 April 2003 395 399
30. G. Pellegrini, L. de Arcangelis, H. Herrmann, and C. Perrone-Capano Activity-dependent neural network model on scale-free networks Phys. Rev. E 76 July 2007 016107:1-9
31. J. Andrade, H. Herrmann, R. Andrade, and L. da Silva Apollonian networks: simultaneously scale-free, small world, Euclidean, space filling, and with matching graphs Phys. Rev. Lett. 94 January 14 2005 018702:1-4
32. M.M. Gupta, L. Jin, and N. Homma Static and Dynamic Neural Networks 2003 IEEE Press New Jersey
33. M. Powell Restart procedures for conjugate gradient method Math. Program. 12 December 1977 241 254
34. D. Mackay Bayesian interpolation Neural Comput. 4 May 1992 415 447
35. S. Makridakis, and M. Hibon The M3-competition: results, conclusions and implications Int. J. Forecast. 16 OctoberDecember 2000 451 476
36. D. Nguyen, B. Widrow, Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights, in: Proc. of the Int. Joint Conf. on Neural Networks, 1990, pp. 2126.
37. J. Tsai, J. Chou, and T. Liu Tuning the structure and parameters of a neural network by using hybrid Taguchi-genetic algorithm IEEE Trans. Neural Netw. 17 January 2006 69 80
38. S. Balkin The value of nonlinear models in the M3-competition Int. J. Forecast. 17 OctoberDecember 2001 545 546
39. J. Cendrowska PRISM: an algorithm for inducing modular rules Int. J. ManMach. Stud. 27 October 1987 349 370
40. T.-S. Lim, W.-Y. Loh, and Y.-S. Shih A comparison of prediction accuracy, complexity, and training time of thirty-three old and new classification algorithms Mach. Learn. 40 September 2000 203 229