Quaternion-based Deep Belief Networks fine-tuning

• Autor(a) principal: Papa, Joao Paulo [UNESP]
• Data de Publicação: 2017
• Outros Autores: Rosa, Gustavo H. [UNESP], Pereira, Danillo R. [UNESP], Yang, Xin-She
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Repositório Institucional da UNESP
• Texto Completo: http://dx.doi.org/10.1016/j.asoc.2017.06.046; http://hdl.handle.net/11449/163439
• topic: Deep Belief Networks; Quaternion; Harmony Search

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. (C) 2017 Elsevier B.V. All rights reserved.