Evolving Deep Networks Using HPC
Author/Presenter
Event Type
Workshop
Deep Learning
Machine Learning
SIGHPC Workshop
TimeMonday, November 13th5:06pm -
5:30pm
Location502-503-504
DescriptionWhile a large number of deep learning networks have
been studied and published that produce outstanding
results on natural image datasets, these datasets only
make up a fraction of those to which deep learning can
be applied. These datasets include text data, audio
data, and arrays of sensors that have very different
characteristics than natural images. As these "best"
networks for natural images have been largely discovered
through experimentation and cannot be proven optimal on
some theoretical basis, there is no reason to believe
that they are the optimal network for these drastically
different datasets. Thus, hyperparameter search is often
a very important process when applying deep learning to
a new problem. In this work, we present an evolutionary
approach to searching the possible space of network
hyperparameters and construction that can scale to
18,000 nodes. This approach is applied to datasets of
varying types and characteristics where we demonstrate
the ability to rapidly find best hyperparameters in
order to reduce enable practitioners to quickly iterate
between idea and result.
Author/Presenter
