Penggabungan Struktur Kernel untuk Desain Jaringan Saraf Hibrida
Article Sidebar
Main Article Content
Abstract
Makalah ini bertujuan untuk mengembangkan classifier jaringan saraf tiruan berbasis fusi struktur kernel untuk meningkatkan kinerja jaringan BP dan RBF tunggal. Solusi yang diusulkan tidak bergantung pada kerangka kerja jaringan RBF dan BP tunggal. Jaringan yang menyatu dapat secara efektif mengekstrak karakteristik lokal dari distribusi spasial sampel dan pembelajaran dan klasifikasi non-linier dalam ruang kernel Gaussian dengan membangun mekanisme koneksi yang efektif antara kernel Gaussian dengan parameter berbeda dan kernel sigmoid di lapisan tersembunyi yang berbeda. Kelebihan jaringan RBF dan BP digabungkan dalam bentuk jaringan yang menyatu. Dalam jaringan RBF dan BP tunggal, ini secara efektif menurunkan ketergantungan pada pemilihan parameter node tersembunyi. Eksperimen pada dua set data simulasi dan tiga set data benchmark menunjukkan bahwa topologi jaringan yang diusulkan lebih disukai.
Article Details
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with FIDELITY : Jurnal Teknik Elektro agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
Jurnal FIDELITY : Jurnal Teknik Elektro is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Accepted 2019-04-28
Published 2019-05-30
References
D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning representations of back-propagating errors", Nature, vol. 323, pp. 533-536, 1986.
D. S. Broomhead,and D. Lowe, "Multivariable function interpolation and adaptive network", Complex Systems, vol. 2, pp. 321-355, 1988.
Y. Liu, J. Yang, L. Li and W. Wu, "Negative effects of sufficiently small initial weights on back-propagation neural networks", Journal of Zhejiang University-SCIENCE C-Computers & Electronics, vol. 13, pp. 585-592, 2012.
S. F. Ding, C. Y. Su and J. Z. Yu, "An optimizing BP neural network algorithm based on genetic algorithm", Artificial Intelligence Review, vol. 36, pp. 153-162, 2011.
A. Bhaya, and E.Kaszkurewicz, "Steepest descent with momentum for quadratic functions is a version of the conjugate gradient method", Neural Networks, vol. 17, pp. 65-71, 2004.
J. E. Vetela and J. Reifman, "Premature saturation in back-propagation networks: mechanism and necessary conditions", Neural Networks, vol. 10, pp. 721-735, 1997.
C. H. Chen, T. K. Yao, C. M. Kuo and C.Y. Chen, "Evolutionary design of constructive multilayer feedforward neural network", Journal of Vibration and Control, vol. 19, pp. 2413-2420, 2013.
S. Amari, "A theory of adaptive pattern classifiers", IEEE Transactions on Electronic Computers, vol. 16, pp. 299-307, 1967.
L. Yingwei, N. Sundararajan and P. Saratchandran, "A sequential learning scheme for function approximation using minimal radial basis function", Neural Computation, vol. 9, pp. 461-478, 1997.
G-B. Huang, P. Saratchandran and N. Sundararajan, "A generalized growing and pruning RBF (GAP-RBF) neural network for function approximation", IEEE Trans. Neural. Netw. vol. 16, 57-67, 2005.
H. Yu, P. D. Reiner, T. Xie, T. Bartczak and B. M. Wilamowski, "An incremental design of radial basis function networks", IEEE Trans. Neural Netw. and Learning Systems, vol. 2, pp. 1793-1803, 2014.
S. Suresh, D. Keming, H. J. Kim, "A sequential learning algorithm for self-adaptive resource allocation network classifier", Neurocomputing, vol. 73, pp. 3012-3019, 2010.
J. Moody and C. J. Darken, "Fast learning in networks of locally-tuned processing", Neural Computation, 1989, vol. 1, pp. 281-294, 1989.
A. D. Niros and G. E. Tsekouras, "A novel training algorithm for RBF neural network using a hybrid fuzzy clustering approach", Fuzzy Sets and Systems, vol. 193, pp. 62-84, 2012.
S. Chen, X. Hong, C. J. Harris and L. Hanzo, "Fully complex-valued radial basis function networks: Orthogonal least squares regression and classification", Neurocomputing, vol. 71, pp. 3421-3433, 2008.