An optimization method for the topological structures of feed-forward multi-layer neural networks

Pattern Recognition

Volumn 31, Issue 9, 1998, Pages 1337-1342

  Daqi, Gao ^a   Shouyi, Wu ^a  

^a JIANGSU UNIVERSITY OF SCIENCE AND TECHNOLOGY   (China)

Author keywords

Artificial neural networks; Empirical formula; Error; Linear basis function; Topological structures

Indexed keywords

ALGORITHMS; BACKPROPAGATION; ERRORS; FUNCTIONS; LEARNING SYSTEMS; MULTILAYER NEURAL NETWORKS; OPTIMIZATION;

EMPIRICAL FORMULA; LINEAR BASIS FUNCTION; TOPOLOGICAL STRUCTURE;

FEEDFORWARD NEURAL NETWORKS;

EID: 0032164306     PISSN: 00313203     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0031-3203(97)00160-X     Document Type: Article

References (54)

1. R. P. Lippmann, An introduction to computing with neural nets, IEEE ASSP Mag., 4, 4-22 (1987).
2. R. P. Gorman and T. J. Sejnowski, Analysis of hidden units in a layered network trained to classify sonar target, Neural Networks 1, 75-89 (1988).
3. S. Y. Kung and J. N. Hwang, An algebraic projection analysis of optimal hidden unit size and learning rate in back propagation learning, IEEE Proc. Int. Conf. Neural Networks, San Diego, California, 363-370 (1988).
4. Qiuzhen Xue, Yu Hen Hu and P. Milenkovic, Analysis of hidden units of multi-layer perceptron and its application in acoustic-to-articulatory mapping, Proc. ICASSP (1990).
5. J. Sietsma and R. J. F. Dow, Neural net pruning - why and how. Proc. IJCNN 1, 325-333 (1988).
6. O. Fujita, Optimization of the hidden units function in feedforward neural networks, Neural Networks 5, 755-764 (1992).
7. M. Hagiwara, Novel backpropagation algorithm for reduction of hidden units and acceleration of convergence using artificial selection, Proc. IJCNN 2, 625-630 (1990).
8. R. Reed, Pruning algorithms: a survey, IEEE Trans. Neural Networks 4(5), 740-747 (1994).
9. Gagan Mirchandani and Wei Cao, On hidden nodes for neural nets, IEEE Trans. Circuits Systems 36(5), 661-664 (1992).
10. I-Chang Jou, Shin-Shien You and Long-wen Chang, Analysis of hidden nodes for multi-layer perceptron neural networks, Pattern Recognition 27(6), 859-864 (1994).
11. R. Battiti, Using mutual information for selecting features in supervised neural network learning, IEEE Trans. Neural Networks 5(4), 537-550 (1994).
12. M. D. Emmerson and R. I. D. Damper, Determining and improving the fault tolerance of multi-layer perceptrons in a pattern-recognition application, IEEE Trans. Neural Networks 5(5), 788-793 (1994).
13. M. G. Bello, Enhanced training algorithms, and integrated training/architecture selection for multilayer perceptron networks, IEEE Trans. Neural Networks 3(6), 864-874 (1992).
14. C. Di Natale and F. A. M. Davide, Sensor arrays calibration with enhanced neural networks, Sensors and Actuators B 18-19, 654-657 (1994).
15. T. Nakamoto, A. Fukuda et al., Perfume and flavor identification by odor-sensing system using quartz-resonator sensor array and neural-network pattern recognition, Sensors and Actuators B 10, 85-90 (1993).
16. G. Niebling, Identification of gases with classical pattern-recognition methods and artificial neural networks, Sensors and Actuators B 18-19, 259-263 (1994).
17. Reza Nekovei and Yang Sun, Back-propagation network and its configuration for blood vessel detection in angiograms, IEEE Trans. Neural Networks 6(1), 64-72 (1995).
18. J. L. Blue, G. T. Gandela and P. J. Grother, Evaluation of pattern classifiers for fingerprint and OCR applications, Pattern Recognition 27(4), 485-501 (1994).
19. D. Valentin, H. Abdi and A. J. O'Toole, Connectionist models of face processing, a survey, Pattern Recognition 27(9), 1209-1230 (1994).
20. Chang Jing Shang and K. Brown, Principal feature-based feature classification with neural networks, Pattern Recognition 27(5), 675-687 (1994).
21. V. R. de Angulo and C. Torras, On-line learning with minimal digression in feedforward networks, IEEE Trans. Neural Networks 6(3), 657-668 (1995).
22. J. H. Kim and S. K. Park, The geometrical learning of binary neural networks, IEEE Trans. Neural Networks 6(1), 237-247 (1995).
23. H. Gu and H. Takahashi, Toward more practical average bounds on supervised learning, IEEE Trans. Neural Networks 7(4), 953-968 (1996).
24. Ramesh Rangarajan Sarukkai, Supervised self-coding in multi-layered feedforward networks, IEEE Trans. Neural Networks 7(5), 1184-1195 (1996).
25. Hyung-Ki Hong, Hyun Woo Shin, Hyeon Soo Park et al, Gas identification using micro gas sensor array and neural-network pattern recognition, Sensors and Actuators B 33, 68-71 (1996).
26. C. Di Natale, F. A. M. Davide, Arnaldo D' Amico et al., An electronic nose for the recognition of the vineyard of a red wine, Sensors and Actuators B 33, 83-88 (1996).
27. R. A. Fisher, The use of multiple measurements in taxonomic problems, Ann. Eugen 7, 179-188 (1936).
28. C. Khunasaraphan, K. Vanapipat and C. Lursinsap, Weight shifting techniques for self-recovery neural network, IEEE Trans. Neural Networks 5(4), 651-658 (1994).
29. D. S. Chen and C. J. Ramesh, A robust back propagation learning algorithm for function approximate, IEEE Trans. Neural Networks 5(3), 467-475 (1994).
30. M. Di Martino, S. Fanelli and M. Protasi, Exploring and comparing the best "direct methods" for the efficient training of MLP-networks, IEEE Trans. Neural Networks 7(6), 1497-1502 (1996).
31. Angelo Frosini, Marco Gori and Paolo Priami, A neural network-based model for paper currency recognition and verification, IEEE Trans. Neural Networks 7(6), 1482-1490 (1996).
32. Taek Mu Kwon and E. H. Feroz, A multilayered perceptron approach to prediction of the SEC's investigation targets, IEEE Trans. Neural Networks 7(5), 1286-1289 (1996).
33. Raffaele Parisi, Elio D. Di Cludio and Giannio Orlandi, A generalized learning paradigm exploiting the structure of feedforward neural networks, IEEE Trans. Neural Networks 7(6), 1450-1460 (1996).
34. J. P. Drouhard, R. Sabourin Tamura and M. Godbout, A neural network approach to off-line signature using directional PDF, Pattern Recognition 29(3), 415-424 (1996).
35. N. S. Merchawi, S. R. T. Kumara and Chita R. Das, A probabilistic model for the fault tolerance of multi-layer perceptrons, IEEE Trans. Neural Networks 7(1), 201-205 (1996).
36. D. A. Karras and S. J. Perantonis, An efficient constrained training algorithm for feedforward networks, IEEE Trans. Neural Networks 6(6), 1420-1434 (1995).
37. A. A. Ghorbani and V. C. Bhavsar, Incremental communication for multilayer neural networks, IEEE Trans. Neural Networks 6(5) 1375-1385 (1995).
38. L. Poetro Cordella, Claudio De Stefano, Francesco Tortorella et al., A method for improving classification reliability of multilayer perceptrons, IEEE Trans. Neural Networks 6 (5), 1140-1147 (1995).
39. Young-Chul Kim and M. A. Shanldott, Architecture and statistical model of a pulse-mode digital multilayer neural network, IEEE Trans. Neural Networks 6(5), 1109-1118 (1995).
40. S. Chakrabarti, N. Bindal and K. Theagharajan, Robust radar target classifier using artificial neural networks, IEEE Trans. Neural Networks 6(3), 760-766 (1995).
41. D. Naylor, S. Jones and D. Myers, Backpropagation in linear arrays - a performance analysis and optimiziation, IEEE Trans. Neural Networks 6(3), 583-595 (1995).
42. P. Kerlirzin and P. Refregier, Theoretical investigation of the robustness of multilayer perceptrons: analysis of the linear case and extension to nonlinear networks, IEEE Trans. Neural Networks 6(3), 560-571 (1995).
43. Soheil Shams and Lean-Luc Gaudiot, Implementing regularly structured neural networks on the DREAM machine, IEEE Trans. Neural Networks 6(2), 407-421 (1995).
44. Young-Chul Kim and Michael A. Shanldott, Random noise effects in pulse-mode digital multilayer neural network, IEEE Trans. Neural Networks 6(1), 220-229 (1995).
45. Urs A. Muller, Anton Gunzinger and Walter Guggenbuhl, Fast neural net simulation with a DSP processor array, IEEE Trans. Neural Networks 6(1), 203-213 (1995).
46. D. Vlachos and J. Avarisiotis, Fuzzy neural networks for gas sensing, Sensors and Actuators B 33, 83-88 (1996).
47. R. Anand, K. Mehrotra and K. Mohan, Efficient classification for multiclass problem using modular neural networks, IEEE Trans. Neural Networks 6(1), 117-124 (1995).
48. Fumiaki Takeda and Sigeru Omatu, High speed paper currency by neural network, IEEE Trans. Neural Networks 6(1), 73-77 (1995).
49. S. Ergezinger and E. Thomsen, An accelerated learning algorithm for multilayer perceptron: optimization layer by layer, IEEE Trans. Neural Networks 6(1), 31-42 (1995).
50. S. Singh, E. L. Hines and J. W. Gardner, Fuzzy neural computing of coffee and tainted-water data from an electronic nose, Sensors and Actuators B 30, 185-190 (1996).
51. K. I. Diamantaras and Sun-Yuan Kung, Multilayer neural networks for reduced-rank applications, IEEE Trans. Neural Networks 5(5), 684-687 (1994).
52. J. Ting-Ho Lo, Synthetic approach to optimal filtering, IEEE Trans. Neural Networks 5(5), 803-811 (1994).
53. Zheru Chi, Mark Suters and Hong Yan, Hardwritten digit recognition using combined ID3-derived fuzzy rules and markov chains, Pattern Recognition 29(11), 1821-1823 (1996).
54. D. B. Fogal, An information criterion for optimal neural network selection, IEEE Trans. Neural Networks 2(5), 490-497 (1991).