Алгоритм побудови експертних систем на ґрунті штучних нейронних мереж
DOI:
https://doi.org/10.18372/1990-5548.51.11701Ключові слова:
експертна система, штучна нейронна мережа, метод Левенберга—Марквардта, радіальна базисна функція, електроенцефалограмиАнотація
Розглянуто алгоритм побудови експертних систем за допомогою навчання багатошарової штучної нейронної мережі. Запропоновано алгоритм оптимізації вагів штучної мережі за методом Левенберга—Марквардта.Ефективність навчання штучної нейронної мережі продемонстровано на прикладі класифікації електроенцефалограм.
Посилання
Y. H. Cheng and C. S. Lin, “Learning algorithm for radial basis function network with the capability of adding and pruning neurons.” Proc. 1994 Conf. ICNN. Orlando, 1994, pp. 797–801.
S. Osowski and K. Siwek, “Selforganizing neural networks for short term load forecasting in power system.” Engineering Applications of Neural Networks (EANN), pp. 253–256, 1998.
T. Desell, S. Clachar, J. Higgins, and B. Wild, “Evolving Deep Recurrent Neural Networks Using Ant Colony Optimization.” Evolutionary Computation in Combinatorial Optimization. vol. 9026, pp. 86–98, 2015.
M. S. Popova and V. V. Strijov, “Building superposition of deep learning neural networks for solving the problem of time series classification.” Systems and Means of Informatics, vol. 25, no. 3, pp. 60–77, 2015.
S. Ioffe and C. Szegedy, “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift.” [E-resource] arXiv.org. 2015. http://arxiv.org/abs/1502.03167.
N.Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever and R. Salakhutdinov. “Dropout: A Simple Way to Prevent Neural Networks from Overfitting.” Journal of Machine Learning Research, 15: 1929–1958. 2014.
Z. Li, C. Chang, F. Liang and others, “Learning Locally-Adaptive Decision Functions for Person Verification.” Computer Vision and Pattern Recognition: Proceedings of the 2013 IEEE Conference. 2013, pp. 3610–3617.
##submission.downloads##
Номер
Розділ
Ліцензія
Authors who publish with this journal 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 License that allows others to share the work with an acknowledgement 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 acknowledgement 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 (See The Effect of Open Access).