DOE OSTI · 1495999
Ramifications of Evolving Misbehaving Convolutional Neural Network Kernel and Batch Sizes
Abstract
Deep-learners have many hyper-parameters including learning rate, batch size, kernel size - all playing a significant role toward estimating high quality models. Discovering useful hyper-parameter guidelines is an active area of research, though the state of the art generally uses a brute force, uniform grid approach or random search for finding ideal settings. We share the preliminary results of using an alternative approach to deep learner hyper-parameter tuning that uses an evolutionary algorithm to improve the accuracy of a deep-learner models used in satellite imagery building footprint detection. We found that the kernel and batch size hyper-parameters surprisingly differed from sizes arrived at via a brute force uniform grid approach. These differences suggest a novel role for evolutionary algorithms in determining the number of convolution layers, as well as smaller batch sizes in improving deep-learner models.
Keep this discovery
Explore connections, maps & timelines
Coletti, Mark, Lunga, Dalton, Berres, Andy, Sanyal, Jibo, Rose, Amy. 2018-11-01. Ramifications of Evolving Misbehaving Convolutional Neural Network Kernel and Batch Sizes. https://doi.org/10.1109/mlhpc.2018.8638644. https://searchnasa.com/record/osti%3A1495999/ramifications-of-evolving-misbehaving-convolutional-neural-network-kernel-and-batch-sizes
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Search NASA by Indiciae: BibTeX · RIS.