Animating neural network training

dc.contributor.author	van der Poel, E
dc.contributor.author	Cloete, I
dc.date.accessioned	2018-05-23T11:10:35Z
dc.date.available	2018-05-23T11:10:35Z
dc.date.issued	1992
dc.identifier.citation	Van der Poel E & Cloete I (1992) Animating neural network training. The South African Computer Journal, Number 7, 1992	en
dc.identifier.issn	2313-7835
dc.identifier.uri	http://hdl.handle.net/10500/24041
dc.description.abstract	In Artificial Neural Network (ANN) simulation it is usually necessary to examine the behaviour of the ANN and detect problems if they occur. However, due to the large volume and high dimensionality of data generated during ANN simulation, interpretation of results is difficult. By using visualisation techniques, such as simple animated faces, problems that occur during the training of a back-propagation neural network can be detected and analyzed. The dynamic behaviour of the network is also better understood when using animation as part of the visualization process.	en
dc.language.iso	en	en
dc.publisher	South African Computer Society (SAICSIT)	en
dc.subject	Neural networks	en
dc.subject	Back-propagation	en
dc.subject	Visualization	en
dc.title	Animating neural network training	en
dc.type	Article	en