Approximate Solutions of Initial Value Problems for Ordinary Differential Equations Using Radial Basis Function Networks

We present a numerical approach for the approximate solutions of first order initial value problems (IVP) by using unsupervised radial basis function networks. The proposed unsupervised method is able to solve IVPs with high accuracy. In order to demonstrate the efficiency of the proposed approach, we also compare its solutions with the solutions obtained by a previously proposed neural network method for representative examples.

[1]  Alireza Nazemi,et al.  A Neural Network Approach for Solving Optimal Control Problems with Inequality Constraints and Some Applications , 2017, Neural Processing Letters.

[2]  Dimitrios I. Fotiadis,et al.  Artificial neural networks for solving ordinary and partial differential equations , 1997, IEEE Trans. Neural Networks.

[3]  Gilles Pagès,et al.  Approximations of Functions by a Multilayer Perceptron: a New Approach , 1997, Neural Networks.

[4]  Snehashish Chakraverty,et al.  Comparison of Artificial Neural Network Architecture in Solving Ordinary Differential Equations , 2013, Adv. Artif. Neural Syst..

[5]  Mohsen Hayati,et al.  Multilayer perceptron neural networks with novel unsupervised training method for numerical solution of the partial differential equations , 2009, Appl. Soft Comput..

[6]  Dumitru Baleanu,et al.  Artificial neural network approach for a class of fractional ordinary differential equation , 2016, Neural Computing and Applications.

[7]  A. Cichocki,et al.  Neural networks for solving systems of linear equations and related problems , 1992 .

[8]  S. Effati,et al.  Artificial Neural Networks Approach for Solving Stokes Problem , 2010 .

[9]  Snehashish Chakraverty,et al.  Single Layer Chebyshev Neural Network Model for Solving Elliptic Partial Differential Equations , 2016, Neural Processing Letters.

[10]  Xin Li,et al.  Simultaneous approximations of multivariate functions and their derivatives by neural networks with one hidden layer , 1996, Neurocomputing.

[11]  Ju-Hong Lee,et al.  Comparison of generalization ability on solving differential equations using backpropagation and reformulated radial basis function networks , 2009, Neurocomputing.

[12]  Alaeddin Malek,et al.  Solving initial-boundary value problems for systems of partial differential equations using neural networks and optimization techniques , 2009, J. Frankl. Inst..

[13]  Hossein Khosravi,et al.  A Novel Structure for Radial Basis Function Networks—WRBF , 2012, Neural Processing Letters.

[14]  Haidong Qu.  Cosine Radial Basis Function Neural Networks for Solving Fractional Differential Equations , 2017 .

[15]  Omid Khayat,et al.  Performance Verification of a Fuzzy Wavelet Neural Network in the First Order Partial Derivative Approximation of Nonlinear Functions , 2015, Neural Processing Letters.

[16]  Lucie P. Aarts,et al.  Neural Network Method for Solving Partial Differential Equations , 2001, Neural Processing Letters.

[17]  Snehashish Chakraverty,et al.  Applied Soft Computing , 2016 .

[18]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

[19]  Hadi Sadoghi Yazdi,et al.  Unsupervised kernel least mean square algorithm for solving ordinary differential equations , 2011, Neurocomputing.

[20]  Zhixiang Chen,et al.  The construction and approximation of neural networks operators with Gaussian activation function , 2013 .