Smit, P.G.J. (2011) Pulse Based Input for Echo State Neural Networks. Bachelor's Thesis, Artificial Intelligence.
|
Text
5_april.pdf - Published Version Download (247kB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
AkkoordVanElburg.pdf - Other Restricted to Registered users only Download (67kB) |
Abstract
Most papers demonstrating an Echo State Neural Network (ESNN) use a scale measure input to control the output. In this paper we describe and show the results for 6 different scenarios to find out what pulse-based amplitude modulation method is best. In these scenarios we vary the information offered on the pulse amplitude and the pulse width. Is information coded on these two independent variables processed with the same error and optimal parameters? Our results show that information on the pulse amplitude yields a lower error compared to information on the pulse width.
| Item Type: | Thesis (Bachelor's Thesis) |
|---|---|
| Degree programme: | Artificial Intelligence |
| Thesis type: | Bachelor's Thesis |
| Language: | English |
| Date Deposited: | 15 Feb 2018 07:47 |
| Last Modified: | 15 Feb 2018 07:47 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/9994 |
Actions (login required)
 |
View Item |