University of Twente Student Theses
Active Learning on Embedded Devices
Boer, Frans de (2021) Active Learning on Embedded Devices.
|
PDF
12MB |
| Abstract: | Machine Learning algorithms require a lot of resources to predict, and even more resources to be trained. This makes it very difficult to train machine learning algorithms on embedded devices, which typically have a small battery and low power processors. This low power processor allows the device to last a long time on a small battery, but it also means tasks that require a lot of resources are difficult to implement. This research aims to use active learning to reduce the number of training iterations required to achieve a high accuracy on a machine learning problem, and thus make it more feasible to train machine learning algorithms on low powered devices. In the end we show that while our active learning algorithms had some problems, energy usage was still reduced and it could be a promising way of reducing the energy usage of machine learning algorithms. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Computer Science BSc (56964) |
| Link to this item: | https://purl.utwente.nl/essays/86856 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page