Jafarian, AhmadNia, Safa MeasoomyGolmankhaneh, Alireza KhaliliBaleanu, Dumitru02.02. Matematik02. Fen-Edebiyat Fakültesi01. Çankaya Üniversitesi2020-03-172025-09-182020-03-172025-09-182018Jafarian, Ahmad...et al. (2018). "On artificial neural networks approach with new cost functions", Applied Mathematics and Computation, Vol. 339, pp. 546-555.0096-30031873-5649https://doi.org/10.1016/j.amc.2018.07.053https://hdl.handle.net/123456789/10404Khalili Golmankhaneh, Alireza/0000-0002-5008-0163In this manuscript, the artificial neural networks approach involving generalized sigmoid function as a cost function, and three-layered feed-forward architecture is considered as an iterative scheme for solving linear fractional order ordinary differential equations. The supervised back-propagation type learning algorithm based on the gradient descent method, is able to approximate this a problem on a given arbitrary interval to any desired degree of accuracy. To be more precise, some test problems are also given with the comparison to the simulation and numerical results given by another usual method. (C) 2018 Elsevier Inc. All rights reserved.eninfo:eu-repo/semantics/closedAccessFractional Order Ordinary Differential EquationArtificial Neural Networks ApproachLeast Mean Squares Cost FunctionSupervised Back-Propagation Learning AlgorithmArticle10.1016/j.amc.2018.07.0532-s2.0-85051662269