Quaternion-based deep belief networks fine-tuning

Papa, João Paulo, Rosa, Gustavo H., Pereira, Danillo R. and Yang, Xin-She ORCID: https://orcid.org/0000-0001-8231-5556 (2017) Quaternion-based deep belief networks fine-tuning. Applied Soft Computing, 60 . pp. 328-335. ISSN 1568-4946 (doi:10.1016/j.asoc.2017.06.046)

[img]
Preview
PDF - Final accepted version (with author's formatting)
Available under License Creative Commons Attribution-NonCommercial-NoDerivatives.

Download (553kB) | Preview

Abstract

Deep learning techniques have been paramount in the last years, mainly due to their outstanding results in a number of applications. In this paper, we address the issue of fine-tuning parameters of Deep Belief Networks by means of meta-heuristics in which real-valued decision variables are described by quaternions. Such approaches essentially perform optimization in fitness landscapes that are mapped to a different representation based on hypercomplex numbers that may generate smoother surfaces. We therefore can map the optimization process onto a new space representation that is more suitable to learning parameters. Also, we proposed two approaches based on Harmony Search and quaternions that outperform the state-of-the-art results obtained so far in three public datasets for the reconstruction of binary images.

Item Type: Article
Research Areas: A. > School of Science and Technology > Design Engineering and Mathematics
Item ID: 22275
Depositing User: Xin-She Yang
Date Deposited: 24 Jul 2017 15:54
Last Modified: 10 Jun 2019 21:13
URI: https://eprints.mdx.ac.uk/id/eprint/22275

Actions (login required)

Edit Item Edit Item

Full text downloads (NB count will be zero if no full text documents are attached to the record)

Downloads per month over the past year