Solving parametric PDE problems with artificial neural networks
نویسندگان
چکیده
The curse of dimensionality is commonly encountered in numerical partial differential equations (PDE), especially when uncertainties have to be modeled into the equations as random coefficients. However, very often the variability of physical quantities derived from PDE can be captured by a few features on the space of random coefficients. Based on such observation, we propose using neural-network, a technique gaining prominence in machine learning tasks, to parameterize the physical quantity of interest as a function of random input coefficients. The simplicity and accuracy of the approach are demonstrated through notable examples of PDEs in engineering and physics.
منابع مشابه
Solving nonlinear Lane-Emden type equations with unsupervised combined artificial neural networks
In this paper we propose a method for solving some well-known classes of Lane-Emden type equations which are nonlinear ordinary differential equations on the semi-innite domain. The proposed approach is based on an Unsupervised Combined Articial Neural Networks (UCANN) method. Firstly, The trial solutions of the differential equations are written in the form of feed-forward neural networks cont...
متن کاملOn the convergence speed of artificial neural networks in the solving of linear systems
Artificial neural networks have the advantages such as learning, adaptation, fault-tolerance, parallelism and generalization. This paper is a scrutiny on the application of diverse learning methods in speed of convergence in neural networks. For this aim, first we introduce a perceptron method based on artificial neural networks which has been applied for solving a non-singula...
متن کاملA Neural Network Model to Solve DEA Problems
The paper deals with Data Envelopment Analysis (DEA) and Artificial Neural Network (ANN). We believe that solving for the DEA efficiency measure, simultaneously with neural network model, provides a promising rich approach to optimal solution. In this paper, a new neural network model is used to estimate the inefficiency of DMUs in large datasets.
متن کاملOptimizing Multiple Response Problem Using Artificial Neural Networks and Genetic Algorithm
This paper proposes a new intelligent approach for solving multi-response statistical optimization problems. In most real world optimization problems, we are encountered adjusting process variables to achieve optimal levels of output variables (response variables). Usual optimization methods often begin with estimating the relation function between the response variable and the control variab...
متن کاملStock price analysis using machine learning method(Non-sensory-parametric backup regression algorithm in lin-ear and nonlinear mode)
The most common starting point for investors when buying a stock is to look at the trend of price changes. In recent years, different models have been used to predict stock prices by researchers, and since artificial intelligence techniques, including neural networks, genetic algorithms and fuzzy logic, have achieved successful re-sults in solving complex problems; in this regard, more exploita...
متن کامل