- author = "Pedro Carvalho and Nuno Lourenco and Penousal Machado",
- title = "Evolving Adaptive Neural Network Optimizers for Image Classification",
- booktitle = "EuroGP 2022: Proceedings of the 25th European Conference on Genetic Programming",
- year = "2022",
- editor = "Eric Medvet and Gisele Pappa and Bing Xue",
- series = "LNCS",
- volume = "13223",
- publisher = "Springer Verlag",
- address = "Madrid, Spain",
- pages = "3--18",
- month = "20-22 " # apr,
- organisation = "EvoStar, Species",
- keywords = "genetic algorithms, genetic programming, Grammatical Evolution, ANN, Neuroevolution, Adaptive Optimizers, Structured Grammatical Evolution",
- isbn13 = "978-3-031-02055-1",
-
URL = "
https://www.human-competitive.org/sites/default/files/humiessubmission_2.txt",
-
URL = "
https://www.human-competitive.org/sites/default/files/evolving_adaptive_neural_network_optimizers_for_image_classification_2.pdf",
-
DOI = "
doi:10.1007/978-3-031-02056-8_1",
- size = "16 pages",
-
abstract = "The evolution of hardware has enabled Artificial
Neural Networks to become a staple solution to many
modern Artificial Intelligence problems such as natural
language processing and computer vision. The neural
network effectiveness is highly dependent on the
optimizer used during training, which motivated
significant research into the design of neural network
optimizers. Current research focuses on creating
optimizers that perform well across different
topologies and network types. While there is evidence
that it is desirable to fine-tune optimizer parameters
for specific networks, the benefits of designing
optimizers specialized for single networks remain
mostly unexplored.
we propose an evolutionary framework called Adaptive AutoLR (ALR) to evolve adaptive optimizers for specific neural networks in an image classification task. The evolved optimizers are then compared with state-of-the-art, human-made optimizers on two popular image classification problems. The results show that some evolved optimizers perform competitively in both tasks, even achieving the best average test accuracy in one dataset. An analysis of the best evolved optimizer also reveals that it functions differently from human-made approaches. The results suggest ALR can evolve novel, high-quality optimizers motivating further research and applications of the framework.",
-
notes = "Entered 2022
HUMIES
http://www.evostar.org/2022/eurogp/ Part of \cite{Medvet:2022:GP} EuroGP'2022 held inconjunction with EvoApplications2022 EvoCOP2022 EvoMusArt2022",
