Portal de Periódicos da CAPES

Artigo Acesso aberto Produção Nacional Revisado por pares

BIBTEX RIS

Quaternion-based Deep Belief Networks fine-tuning

2017; Elsevier BV; Volume: 60; Linguagem: Inglês

10.1016/j.asoc.2017.06.046

1872-9681

João Paulo Papa, Gustavo Henrique de Rosa, Danillo Roberto Pereira, Xin‐She Yang,

Advanced Image Processing Techniques

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.