| Texto completo | |
| Autor(es): |
Ferreira, Martha Dais
[1]
;
Correa, Debora Cristina
[1, 2]
;
Nonato, Luis Gustavo
[1]
;
de Mello, Rodrigo Fernandes
[1]
Número total de Autores: 4
|
| Afiliação do(s) autor(es): | [1] Univ Sao Paulo, Inst Math & Comp Sci, Av Trabalhador Saocarlense 400, BR-13566590 Sao Carlos, SP - Brazil
[2] Univ Western Australia, Sch Math & Stat, 35 Stirling Highway, Perth, WA 6009 - Australia
Número total de Afiliações: 2
|
| Tipo de documento: | Artigo Científico |
| Fonte: | EXPERT SYSTEMS WITH APPLICATIONS; v. 94, p. 205-217, MAR 15 2018. |
| Citações Web of Science: | 12 |
| Resumo | |
The Convolutional Neural Network (CNN) figures among the state-of-the-art Deep Learning (DL) algorithms due to its robustness to support data shift, scale variations, and its capability of extracting relevant information from large-scale input data. However, setting appropriate parameters to define CNN architectures is still a challenging issue, mainly to tackle real-world problems. A typical approach consists in empirically assessing different CNN settings in order to select the most appropriate one. This procedure has clear limitations, including the choice of suitable predefined configurations as well as the high computational cost involved in evaluating each of them. This work presents a novel methodology to tackle the previously mentioned issues, providing mechanisms to estimate effective CNN configurations, including the size of convolutional masks (convolutional kernels) and the number of convolutional units (CNN neurons) per layer. Based on the False Nearest Neighbors (FNN), a well-known tool from the area of Dynamical Systems, the proposed method helps estimating CNN architectures that are less complex and produce good results. Our experiments confirm that architectures estimated through the proposed approach are as effective as the complex ones defined by empirical and computationally intensive strategies. (C) 2017 Elsevier Ltd. All rights reserved. (AU) | |
| Processo FAPESP: | 11/22749-8 - Desafios em visualização exploratória de dados multidimensionais: novos paradigmas, escalabilidade e aplicações |
| Beneficiário: | Luis Gustavo Nonato |
| Modalidade de apoio: | Auxílio à Pesquisa - Temático |
| Processo FAPESP: | 14/13323-5 - Abordagem baseada na estabilidade de algoritmos de agrupamento de dados para garantir a detecção de mudanças de conceito em fluxos de dados |
| Beneficiário: | Rodrigo Fernandes de Mello |
| Modalidade de apoio: | Auxílio à Pesquisa - Regular |
| Processo FAPESP: | 12/17961-0 - Mineração de Dados Musicais Baseada em Padrões Temporais |
| Beneficiário: | Débora Cristina Corrêa |
| Modalidade de apoio: | Bolsas no Brasil - Pós-Doutorado |