Improving neural network approximations in applications: case study in materials science

Title:

Improving neural network approximations in applications: case study in materials science

Creator:

Holeňa, Martin and Steinfeldt, Norbert

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:9fb01b04-5935-44fd-8b24-6c9bf3ae254b
uuid:9fb01b04-5935-44fd-8b24-6c9bf3ae254b

Subject:

Artificial neural networks, approximation capability, and crossvalidation

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

The popularity of feed-forward neural networks such as multilayer perceptrons and radial basis function networks is to a large extent due to their universal approximation capability. This paper concerns its theoretical principles, together with the influence of network architecture and of the distribution of training data on this capability. Then, the possibility to exploit this influence in order to improve the approximation capability of multilayer perceptrons by means of cross-validation and boosting is explained. Although in theory, the impact of both methods on the approximation capability of feed-forward networks is known, they are still not common in real-world applications. Therefore, the paper documents usefulness of both methods on a detailed case study in materials science.

Language:

English

Rights:

http://creativecommons.org/publicdomain/mark/1.0/
policy:public

Source:

Neural network world: international journal on neural and mass-parallel computing and information systems | 2009 Volume:19 | Number:2

Harvested from:

CDK

Metadata only:

false