<div dir="ltr"><br clear="all"><div><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div dir="ltr"><br></div></div></div></div></div></div><div class="gmail_quote"><div dir="ltr"><div><div style="overflow:auto"><div style="max-height:10000px"><div dir="ltr"><p style="text-align:center;clear:both"><a href="https://lh3.googleusercontent.com/-ZPFNPh16sR0/Wt39FrXUP-I/AAAAAAAAAaw/3wQunGe20lUopmV_ggfPaDwE9cVAgVzxgCLcBGAs/s1600/image001.jpg" style="margin-left:1em;margin-right:1em" target="_blank"><img src="https://lh3.googleusercontent.com/-ZPFNPh16sR0/Wt39FrXUP-I/AAAAAAAAAaw/3wQunGe20lUopmV_ggfPaDwE9cVAgVzxgCLcBGAs/s1600/image001.jpg" border="0"></a></p><br>
<p class="MsoNormal" style="text-align:center" align="center"><span style="font-family:"Verdana",sans-serif;color:black">DATE:</span><span style="font-size:10.0pt;font-family:"Verdana",sans-serif;color:black"> </span><span style="font-size:13.5pt;font-family:"Verdana",sans-serif;color:black"> </span><b><span style="font-size:18.0pt;font-family:"Verdana",sans-serif">Friday, February 8, 2019</span></b></p>
<p class="MsoNormal" style="text-align:center" align="center"><span style="font-size:10.0pt;font-family:"Verdana",sans-serif;color:black"><br></span></p><p class="MsoNormal" style="text-align:center" align="center"><span style="font-size:10.0pt;font-family:"Verdana",sans-serif;color:black"> </span></p>
<p class="MsoNormal" style="text-align:center" align="center"><span style="font-family:"Verdana",sans-serif;color:black">TITLE:</span><span style="font-size:10.0pt;font-family:"Verdana",sans-serif;color:black"> <br></span></p><p class="MsoNormal" style="text-align:center" align="center"><span style="font-size:10.0pt;font-family:"Verdana",sans-serif;color:black"> <br></span></p><p class="MsoNormal" style="text-align:center" align="center"><font size="6"><span style="font-family:verdana,sans-serif"></span></font></p><p class="MsoNormal" style="text-align:center" align="center"><font size="6"><span style="font-family:verdana,sans-serif"><b><span style="background:white none repeat scroll 0% 0%"></span></b></span></font></p><div style="text-align:center"><span style="font-family:verdana,sans-serif"><font size="6"><b><span></span></b></font></span><span style="font-family:verdana,sans-serif"><font size="6"><b><span></span></b></font></span><span style="font-family:verdana,sans-serif"><font size="6"><b><span></span></b></font></span><span style="font-family:verdana,sans-serif"><font size="6"><b><span>Deep Learning Evolutionary Optimization for Regression of Rotorcraft Vibrational Spectra</span></b></font><br></span><span style="font-family:verdana,sans-serif"><font size="6"><b><span style="font-size:11pt"></span></b> </font></span></div><p class="MsoNormal" style="text-align:center" align="center"><span style="font-family:"Verdana",sans-serif;color:black"> </span></p>
<p class="MsoNormal" style="text-align:center" align="center"><span style="font-family:"Verdana",sans-serif;color:black"><br></span></p><p class="MsoNormal" style="text-align:center" align="center"><span style="font-family:"Verdana",sans-serif;color:black">TIME:</span><span style="font-size:10.0pt;font-family:"Verdana",sans-serif;color:black"> </span><span style="font-size:13.5pt;font-family:"Verdana",sans-serif;color:black"> </span><b><span style="font-size:18.0pt;font-family:"Verdana",sans-serif">3<span style="color:black">:30PM</span></span></b></p>
<p class="MsoNormal" style="text-align:center" align="center"><span style="font-size:10.0pt;font-family:"Verdana",sans-serif;color:black"> </span></p>
<p class="MsoNormal" style="text-align:center" align="center"><span style="font-family:"Verdana",sans-serif;color:black">LOCATION:</span><span style="font-size:10.0pt;font-family:"Verdana",sans-serif;color:black"> <b> </b></span><b><span style="font-size:18.0pt;font-family:"Verdana",sans-serif">GMCS 314</span></b></p>
<p class="MsoNormal" style="text-align:center" align="center"><span style="font-size:10.0pt;font-family:"Verdana",sans-serif;color:black"> </span></p>
<p class="MsoNormal" style="text-align:center" align="center"><span style="font-family:"Verdana",sans-serif;color:black">SPEAKER/BIO:</span><span style="font-size:13.5pt;font-family:"Verdana",sans-serif;color:black"> </span><b><span style="font-size:18.0pt;font-family:"Verdana",sans-serif"><br></span></b></p><p class="MsoNormal" style="text-align:center" align="center"><br><b><span style="font-size:18.0pt;font-family:"Verdana",sans-serif"></span></b></p><p class="MsoNormal" style="text-align:center" align="center"><b><span style="font-size:18.0pt;font-family:"Verdana",sans-serif"></span></b><b><span style="font-size:18.0pt;font-family:"Verdana",sans-serif">Gregory Behm, CEO and owner of Innovative HPC Solutions LLC <br></span></b><font size="4"><span style="font-family:verdana,sans-serif"><b><span><b><span style="font-size:18.0pt;font-family:"Verdana",sans-serif"><span style="color:black"></span></span></b></span><span></span></b></span></font></p><p class="MsoNormal" style="text-align:center" align="center"><b><span style="font-size:18.0pt;font-family:"Verdana",sans-serif"></span></b></p>
<p class="MsoNormal" style="text-align:center" align="center"><span style="font-family:"Verdana",sans-serif;color:black"> </span></p>
<p class="MsoNormal"><span style="font-family:"Verdana",sans-serif;color:black"><br></span></p><p class="MsoNormal"><span style="font-family:"Verdana",sans-serif;color:black">ABSTRACT:</span></p><font size="4"><span style="font-family:verdana,sans-serif">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.
</span></font></div><font size="4"><span style="font-family:verdana,sans-serif"><br></span></font><h2><span style="font-size:11.0pt;font-family:"Verdana",sans-serif;color:black;font-weight:normal">HOST:</span><span style="font-family:"Verdana",sans-serif;color:#1f497d"> </span>Priscilla Kelly, CSRC, SIAM Student Chapter President<font size="4"><span style="font-family:verdana,sans-serif"></span></font></h2></div></div></div></div>
<p></p>
-- <br>
You received this message because you are subscribed to the Google Groups "CSRC Colloquium" group.<br>
To unsubscribe from this group and stop receiving emails from it, send an email to <a href="mailto:csrc.colloquium+unsubscribe@sdsu.edu" target="_blank">csrc.colloquium+unsubscribe@sdsu.edu</a>.<br>
For more options, visit <a href="https://groups.google.com/a/sdsu.edu/d/optout" target="_blank">https://groups.google.com/a/sdsu.edu/d/optout</a>.<br>
</div></div>