Javascript must be enabled for the correct page display

Implementing a neural network for the GPU

Linde, J. van der (2012) Implementing a neural network for the GPU. Bachelor's Thesis, Artificial Intelligence.

[img]
Preview
Text
bachelorthesis.pdf - Published Version

Download (264kB) | Preview
[img] 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 View Item