Multilayer perceptron neural networks with novel unsupervised training method for numerical solution of the partial differential equations

Authors:
Yazdan Shirvany;Mohsen Hayati;Rostam Moradian
Affiliations:
Electronics Department, Faculty of Technology, Razi University, Kermanshah, Iran and Computational Intelligence Research Center, Razi University, Kermanshah, Iran;Electronics Department, Faculty of Technology, Razi University, Kermanshah, Iran and Computational Intelligence Research Center, Razi University, Kermanshah, Iran;Physics Department, Faculty of Science, Razi University, Kermanshah, Iran
Venue:
Applied Soft Computing
Year:
2009

Citing 13
Cited 12

Numerical recipes: the art of scientific computing

Numerical recipes: the art of scientific computing
Stable explicit schemes for equations of the Schro¨dinger type

SIAM Journal on Numerical Analysis
A numerical study of the nonlinear Schro¨dinger equation involving quintic terms

Journal of Computational Physics
An unconditionally stable three-level explicit difference scheme for the Schro¨dinger equation with a variable coefficient

SIAM Journal on Numerical Analysis
DuFort--Frankel-Type Methods for Linear and Nonlinear Schrödinger Equations

SIAM Journal on Numerical Analysis
Efficient finite difference solutions to the time-dependent Schrödinger equation

Journal of Computational Physics
On Convergence and Stability of the Explicit Difference Method for Solution of Nonlinear Schrödinger Equations

SIAM Journal on Numerical Analysis
Multilayer neural networks for solving a class of partial differential equations

Neural Networks
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Numerical solution of elliptic partial differential equation using radial basis function neural networks

Neural Networks - 2003 Special issue: Advances in neural networks research — IJCNN'03
Solution of time-independent Schrödinger equation by the imaginary time propagation method

Journal of Computational Physics
Artificial neural networks for solving ordinary and partial differential equations

IEEE Transactions on Neural Networks
Training feedforward networks with the Marquardt algorithm

IEEE Transactions on Neural Networks

Modified Recursive Least Squares algorithm to train the Hybrid Multilayered Perceptron (HMLP) network

Applied Soft Computing
File access prediction using neural networks

IEEE Transactions on Neural Networks
Unsupervised kernel least mean square algorithm for solving ordinary differential equations

Neurocomputing
Application of feedforward neural network in the study of dissociated gas flow along the porous wall

Expert Systems with Applications: An International Journal
Modified wavelet neural network in function approximation and its application in prediction of time-series pollution data

Applied Soft Computing
An evolutionary framework using particle swarm optimization for classification method PROAFTN

Applied Soft Computing
Multilayer perceptrons and radial basis function neural network methods for the solution of differential equations: A survey

Computers & Mathematics with Applications
Automatic parameter settings for the PROAFTN classifier using hybrid particle swarm optimization

AI'10 Proceedings of the 23rd Canadian conference on Advances in Artificial Intelligence
Solving differential equations with Fourier series and Evolution Strategies

Applied Soft Computing
Solving differential equations by means of feed-forward artificial neural networks

ICAISC'12 Proceedings of the 11th international conference on Artificial Intelligence and Soft Computing - Volume Part I
A new stochastic technique for painlevé equation-I using neural network optimized with swarm intelligence

Computational Intelligence and Neuroscience
Comparison of artificial neural network architecture in solving ordinary differential equations

Advances in Artificial Neural Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper by using MultiLayer Perceptron and Radial Basis Function (RBF) neural networks, a novel method for solving both kinds of differential equation, ordinary and partial differential equation, is presented. From the differential equation and its boundary conditions, the energy function of the network is prepared which is used in the unsupervised training method to update the network parameters. This method was implemented to solve the nonlinear Schrodinger equation in hydrogen atom and triangle-shaped quantum well. Comparison of this method results with analytical solution and two well-known numerical methods, Runge-kutta and finite element, shows the efficiency of Neural Networks with high accuracy, fast convergence and low use of memory for solving the differential equations.