Please use this identifier to cite or link to this item:
Title: Improving convolutional neural network design via variable neighborhood search
Authors: Teresa Finisterra Araújo
Guilherme Moreira Aresta
Bernardo Almada-Lobo
Ana Maria Mendonça
Aurélio Campilho
Issue Date: 2017
Abstract: An unsupervised method for convolutional neural network (CNN) architecture design is proposed. The method relies on a variable neighborhood search-based approach for finding CNN architectures and hyperparameter values that improve classification performance. For this purpose, t-Distributed Stochastic Neighbor Embedding (t-SNE) is applied to effectively represent the solution space in 2D. Then, k-Means clustering divides this representation space having in account the relative distance between neighbors. The algorithm is tested in the CIFAR-10 image dataset. The obtained solution improves the CNN validation loss by over 15% and the respective accuracy by 5%. Moreover, the network shows higher predictive power and robustness, validating our method for the optimization of CNN design. © Springer International Publishing AG 2017.
metadata.dc.type: conferenceObject
Appears in Collections:C-BER - Articles in International Conferences
CEGI - Articles in International Conferences

Files in This Item:
File Description SizeFormat 
  Restricted Access
887.12 kBAdobe PDFView/Open Request a copy

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.