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 [Article] (doi:10.1016/j.asoc.2017.06.046)

Preview

PDF - Final accepted version (with author's formatting) Available under License Creative Commons Attribution-NonCommercial-NoDerivatives 4.0. 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.

Actions (login required)

View Item

Statistics

DownloadsShow export options

Export as CSVXMLJSON

Activity Overview

6 month trend

254Downloads

6 month trend

341Hits

Additional statistics are available via IRStats2.