Fine-tuning deep belief networks using cuckoo search
In the last few years, metaheuristic-driven optimization has been employed to address deep belief network (DBN) model selection, since it provides simple and elegant solutions in a wide range of applications. In this work, we introduce the well-known cuckoo search to fine-tune DBN parameters and val...
| Autores: | , , |
|---|---|
| Formato: | capítulo de livro |
| Estado: | Versión publicada |
| Fecha de publicación: | 2016 |
| País: | Brasil |
| Recursos: | Universidade Estadual Paulista (UNESP) |
| Repositorio: | Repositório Institucional da UNESP |
| Idioma: | inglés |
| OAI Identifier: | oai:repositorio.unesp.br:11449/220834 |
| Acesso em linha: | http://dx.doi.org/10.1016/B978-0-12-804536-7.00003-X http://hdl.handle.net/11449/220834 |
| Access Level: | acceso abierto |
| Palavra-chave: | Cuckoo search Deep belief networks Harmony search Metaheuristic Model selection Particle swarm optimization |
| Resumo: | In the last few years, metaheuristic-driven optimization has been employed to address deep belief network (DBN) model selection, since it provides simple and elegant solutions in a wide range of applications. In this work, we introduce the well-known cuckoo search to fine-tune DBN parameters and validate its effectiveness by comparing it with harmony search, improved harmony search, and particle swarm optimization. The experimental results have been carried out in two public datasets using DBNs with a different number of layers concerning the task of binary image reconstruction. |
|---|