Optimizing Convolutional Neural Networks for Embedded Systems by Means of Neuroevolution

Created by W.Langdon from gp-bibliography.bib Revision:1.7630

@InProceedings{Badan:2019:TPNC,

• author = "Filip Badan and Lukas Sekanina",
• title = "Optimizing Convolutional Neural Networks for Embedded Systems by Means of Neuroevolution",
• booktitle = "International Conference on Theory and Practice of Natural Computing, TPNC 2019",
• year = "2019",
• editor = "Carlos Martin-Vide and Geoffrey Pond and Miguel A. Vega-Rodriguez",
• volume = "11934",
• series = "LNCS",
• pages = "109--121",
• address = "Kingston, ON, Canada",
• month = "9-11 " # dec,
• publisher = "Springer",
• keywords = "genetic algorithms, genetic programming, Evolutionary Algorithm Convolutional neural network Neuroevolution Embedded Systems Energy Efficiency",
• isbn13 = "978-3-030-34499-3",
• DOI = "doi:10.1007/978-3-030-34500-6_7",
• size = "13 pages",
• abstract = "Automated design methods for convolutional neural networks (CNNs) have recently been developed in order to increase the design productivity. We propose a neuroevolution method capable of evolving and optimizing CNNs with respect to the classification error and CNN complexity (expressed as the number of tunable CNN parameters), in which the inference phase can partly be executed using fixed point operations to further reduce power consumption. Experimental results are obtained with TinyDNN framework and presented using two common image classification benchmark problems: MNIST and CIFAR-10.",

}

Genetic Programming entries for Filip Badan Lukas Sekanina

Citations