Neural network application to solve Fredholm integral equations of the second kind
Year
: 2009
Abstract: In this paper, a novel method based on neural networks is presented for solving Fredholm
integral equations of the second kind. In the present approach, we first approximate the
unknown function based on neural network, then substitute the approximate function in the
appropriate error function of the integral equation, and finally train the network with as few
neurons as necessary to achieve the desired accuracy. This novel method, in comparison with
existing numerical methods shows that the use of neural networks provides solutions with
very good generalizations and higher accurac.
integral equations of the second kind. In the present approach, we first approximate the
unknown function based on neural network, then substitute the approximate function in the
appropriate error function of the integral equation, and finally train the network with as few
neurons as necessary to achieve the desired accuracy. This novel method, in comparison with
existing numerical methods shows that the use of neural networks provides solutions with
very good generalizations and higher accurac.
Keyword(s): Fredholm Integral equations,Artficial neural networks,MLPs (Multi-\tLayer
Perceptron networks)
Collections
:
-
Statistics
Neural network application to solve Fredholm integral equations of the second kind
Show full item record
| contributor author | سهراب عفتی | en |
| contributor author | R.Buzhabadi | en |
| contributor author | Sohrab Effati | fa |
| date accessioned | 2020-06-06T13:55:09Z | |
| date available | 2020-06-06T13:55:09Z | |
| date copyright | 8/17/2009 | |
| date issued | 2009 | |
| identifier uri | https://libsearch.um.ac.ir:443/fum/handle/fum/3374731 | |
| description abstract | In this paper, a novel method based on neural networks is presented for solving Fredholm integral equations of the second kind. In the present approach, we first approximate the unknown function based on neural network, then substitute the approximate function in the appropriate error function of the integral equation, and finally train the network with as few neurons as necessary to achieve the desired accuracy. This novel method, in comparison with existing numerical methods shows that the use of neural networks provides solutions with very good generalizations and higher accurac. | en |
| language | English | |
| title | Neural network application to solve Fredholm integral equations of the second kind | en |
| type | Conference Paper | |
| contenttype | External Fulltext | |
| subject keywords | Fredholm Integral equations | en |
| subject keywords | Artficial neural networks | en |
| subject keywords | MLPs (Multi-\tLayer Perceptron networks) | en |
| identifier link | https://profdoc.um.ac.ir/paper-abstract-1012618.html | |
| conference title | چهلمین کنفرانس ریاضی کشور | fa |
| conference location | تهران | fa |
| identifier articleid | 1012618 |