Ameen, SA and Vadera, S ORCID: https://orcid.org/0000-0001-6041-2646
2020,
'Pruning neural networks using multi-armed bandits'
, The Computer Journal, 63 (7)
, pp. 1099-1108.
|
PDF
- Published Version
Available under License Creative Commons Attribution 4.0. Download (452kB) | Preview |
|
![]() |
PDF
- Accepted Version
Restricted to Repository staff only Download (417kB) | Request a copy |
Abstract
The successful application of deep learning has led to increasing expectations of their use in embedded systems. This in turn, has created the need to find ways of reducing the size of neural networks. Decreasing the size of a neural network requires deciding which weights should be removed without compromising accuracy, which is analogous to the kind of problems addressed by multi-arm bandits. Hence, this paper explores the use of multi-armed bandits for reducing the number of parameters of a neural network. Different multi-armed bandit algorithms, namely e-greedy, win-stay, lose-shift, UCB1, KL-UCB, BayesUCB, UGapEb, Successive Rejects and Thompson sampling are evaluated and their performance compared to existing approaches. The results show that multi- armed bandit pruning methods, especially those based on UCB, outperform other pruning methods.
Item Type: | Article |
---|---|
Schools: | Schools > School of Computing, Science and Engineering > Salford Innovation Research Centre |
Journal or Publication Title: | The Computer Journal |
Publisher: | Oxford University Press |
ISSN: | 0010-4620 |
Related URLs: | |
Depositing User: | USIR Admin |
Date Deposited: | 10 Jul 2019 12:53 |
Last Modified: | 16 Feb 2022 02:20 |
URI: | http://usir.salford.ac.uk/id/eprint/51774 |
Actions (login required)
![]() |
Edit record (repository staff only) |