[Faculty] Fwd: [CSRC.COLLOQUIUM] "Deep Learning Evolutionary Optimization for Regression of Rotorcraft Vibrational Spectra"

[Jose Castillo]

<https://lh3.googleusercontent.com/-ZPFNPh16sR0/Wt39FrXUP-I/AAAAAAAAAaw/3wQunGe20lUopmV_ggfPaDwE9cVAgVzxgCLcBGAs/s1600/image001.jpg>

DATE:  *Friday, February 8, 2019*




TITLE:


*Deep Learning Evolutionary Optimization for Regression of Rotorcraft
Vibrational Spectra*




TIME:  *3:30PM*



LOCATION:  *GMCS 314*



SPEAKER/BIO:



*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, SIAM Student Chapter President

-- 
You received this message because you are subscribed to the Google Groups
"CSRC Colloquium" group.
To unsubscribe from this group and stop receiving emails from it, send an
email to csrc.colloquium+unsubscribe at sdsu.edu.
For more options, visit https://groups.google.com/a/sdsu.edu/d/optout.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://engineering.sdsu.edu/pipermail/faculty/attachments/20190205/7c699b98/attachment.html>