Feedforward Neural Networks with Diffused Nonlinear Weight Functions
| dc.creator | Rataj, Artur | |
| dc.date | 2003-10-27 | |
| dc.date | 2005-03-31 | |
| dc.date.accessioned | 2026-07-07T03:20:29Z | |
| dc.date.available | 2026-07-07T03:20:29Z | |
| dc.description | In this paper, feedforward neural networks are presented that have nonlinear weight functions based on look--up tables, that are specially smoothed in a regularization called the diffusion. The idea of such a type of networks is based on the hypothesis that the greater number of adaptive parameters per a weight function might reduce the total number of the weight functions needed to solve a given problem. Then, if the computational complexity of a propagation through a single such a weight function would be kept low, then the introduced neural networks might possibly be relatively fast. A number of tests is performed, showing that the presented neural networks may indeed perform better in some cases than the classic neural networks and a number of other learning machines. | |
| dc.description | 17 pages, 7 figures. Corrected, some parts rewritten | |
| dc.identifier | https://arxiv.org/abs/cs/0310050 | |
| dc.identifier | http://arxiv.org/abs/cs/0310050 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/31846 | |
| dc.subject | Neural and Evolutionary Computing | |
| dc.subject | I.2.6 | |
| dc.title | Feedforward Neural Networks with Diffused Nonlinear Weight Functions | |
| dc.type | text |