DATE:

Friday, February 8th, 2019

TIME:

3:30 PM

LOCATION:

GMCS-314

SPEAKER:

Gregory Behm, CEO and owner of Innovative HPC Solutions LLC

ABSTRACT:

A method for Deep Neural Network (DNN) hyperparameter search using evolutionary
optimization is proposed for nonlinear high-dimensional multivariate regression
problems. Deep networks often lead to extensive hyperparameter searches which
can become an ambiguous process due to network complexity. Therefore, we propose
a user-friendly method that integrates Dakota optimization library, TensorFlow,
and Galaxy HPC workflow management tool to deploy massively parallel function
evaluations in a Genetic Algorithm (GA). Deep Learning Evolutionary Optimization
(DLEO) is the current GA implementation being presented. Compared with random
generated and hand-tuned models, DLEO proved to be significantly faster and better
searching for optimal architecture hyperparameter configurations. Implementing
DLEO allowed us to find models with higher validation accuracies at lower
computational costs in less than 72 hours, as compared with weeks of manual and
random search. Moreover, parallel coordinate plots provided valuable insights about
network architecture designs and their regression capabilities.

HOST:

Priscilla Kelly, CSRC, SDSU SIAM Student Chapter President

DOWNLOAD:

PDF File