Quaternion-based Deep Belief Networks fine-tuning

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...

Descripción completa

Detalles Bibliográficos
Autores: Papa, Joao Paulo [UNESP], Rosa, Gustavo H. [UNESP], Pereira, Danillo R. [UNESP], Yang, Xin-She
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2017
País:Brasil
Institución:Universidade Estadual Paulista (UNESP)
Repositorio:Repositório Institucional da UNESP
Idioma:inglés
OAI Identifier:oai:repositorio.unesp.br:11449/163439
Acceso en línea:http://dx.doi.org/10.1016/j.asoc.2017.06.046
http://hdl.handle.net/11449/163439
Access Level:acceso abierto
Palabra clave:Deep Belief Networks
Quaternion
Harmony Search
Descripción
Sumario: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.