DENSER: Deep Evolutionary Network Structured Representation

Created by W.Langdon from gp-bibliography.bib Revision:1.4504

@Misc{DBLP:journals/corr/abs-1801-01563,
  author =       "Filipe Assuncao and Nuno Lourenco and 
                 Penousal Machado and Bernardete Ribeiro",
  title =        "{DENSER:} Deep Evolutionary Network Structured
                 Representation",
  howpublished = "arXiv",
  year =         "2018",
  edition =      "v3",
  month =        "1 " # jun,
  volume =       "abs/1801.01563",
  keywords =     "genetic algorithms, genetic programming, Grammatical
                 Evolution",
  URL =          "http://www.human-competitive.org/sites/default/files/assuncao-paper-b_0.pdf",
  URL =          "http://arxiv.org/abs/1801.01563",
  size =         "11 pages",
  abstract =     "Deep Evolutionary Network Structured Representation
                 (DENSER) is a novel approach to automatically design
                 Artificial Neural Networks (ANNs) using Evolutionary
                 Computation. The algorithm not only searches for the
                 best network topology (e.g., number of layers, type of
                 layers), but also tunes hyper-parameters, such as,
                 learning parameters or data augmentation parameters.
                 The automatic design is achieved using a representation
                 with two distinct levels, where the outer level encodes
                 the general structure of the network, i.e., the
                 sequence of layers, and the inner level encodes the
                 parameters associated with each layer. The allowed
                 layers and range of the hyper-parameters values are
                 defined by means of a human-readable Context-Free
                 Grammar. DENSER was used to evolve ANNs for CIFAR-10,
                 obtaining an average test accuracy of 94.13percent. The
                 networks evolved for the CIFA--10 are tested on the
                 MNIST, Fashion-MNIST, and CIFAR-100; the results are
                 highly competitive, and on the CIFAR-100 we report a
                 test accuracy of 78.75percent. To the best of our
                 knowledge, our CIFAR-100 results are the highest
                 performing models generated by methods that aim at the
                 automatic design of Convolutional Neural Networks
                 (CNNs), and are amongst the best for manually designed
                 and fine-tuned CNNs.",
  notes =        "See \cite{Assuncao:2019:GPEM}. 2018 HUMIES
                 finalist

                 https://github.com/fillassuncao/denser-models",
}

Genetic Programming entries for Filipe Assuncao Nuno Lourenco Penousal Machado Bernardete Ribeiro

Citations