Linde, J. van der (2012) Implementing a neural network for the GPU. Bachelor's Thesis, Artificial Intelligence.
|
Text
bachelorthesis.pdf - Published Version Download (264kB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
AkkoordWiering.pdf - Other Restricted to Registered users only Download (30kB) |
Abstract
Automatic classification becomes more and more in- teresting as the amount of available data keeps grow- ing. Also, modern computers are equipped with pow- erful hardware specifically designed for processing fast amounts of data, namely the GPU (graphical process- ing unit). We use OpenCL to implement a multilayer perceptron that runs on the GPU. Our implementation scales better than an implementation for the CPU, but this proves to be only an improvement for larger net- works due to the overhead of calculating on a different device.
| Item Type: | Thesis (Bachelor's Thesis) |
|---|---|
| Supervisor name: | Wiering, M. and Codreanu, V. |
| Degree programme: | Artificial Intelligence |
| Thesis type: | Bachelor's Thesis |
| Language: | English |
| Date Deposited: | 15 Feb 2018 07:48 |
| Last Modified: | 02 May 2019 11:33 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/10249 |
Actions (login required)
 |
View Item |