Difference between revisions of "Team:Florida Atlantic/Model"

 
(13 intermediate revisions by the same user not shown)
Line 16: Line 16:
  
 
<img src="https://static.igem.org/mediawiki/2017/archive/2/20/20170929214604%21T--Florida_Atlantic--owlbanner.png">
 
<img src="https://static.igem.org/mediawiki/2017/archive/2/20/20170929214604%21T--Florida_Atlantic--owlbanner.png">
 
+
<div align='justify'>
 
<div class="column full_size">
 
<div class="column full_size">
<h3>Model</h3>
+
<h3 style=" font-size:24px ; ">Model</h3>
<div align="justify">
+
<center><h4>LSTM Machine Learning Model</h4></center>
<p> Artemisinin Biosensor Design</p>
+
<form><fieldset>
<img src="https://static.igem.org/mediawiki/2017/4/40/Artemisisninbiosensor.png">
+
<p style=" font-size:18px ; ">The LSTM model contained two lstm layers
 +
with 300 nodes each. The first lstm layer used dropout with a dropout
 +
probability of 0.5 to avoid overfitting the training data. The third
 +
layer of the network was a fully-connected layer with 150 nodes and
 +
hyperbolic tangent activation function. The output layer contained two
 +
nodes with a softmax activation function.<p>
 +
 
 +
</fieldset>
 +
</form>
 +
 
 +
<img style="max-width:95%;border:3px solid darkred;"src="https://static.igem.org/mediawiki/2017/e/ee/T--Florida_Atlantic--LSTMGraph.png">
 +
 
  
 
</div>
 
</div>
  
 
</html>
 
</html>

Latest revision as of 21:54, 1 November 2017

Florida_Atlantic

Model

LSTM Machine Learning Model

The LSTM model contained two lstm layers with 300 nodes each. The first lstm layer used dropout with a dropout probability of 0.5 to avoid overfitting the training data. The third layer of the network was a fully-connected layer with 150 nodes and hyperbolic tangent activation function. The output layer contained two nodes with a softmax activation function.