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

Line 20: Line 20:
 
<h3 style=" font-size:24px ; ">Model</h3>
 
<h3 style=" font-size:24px ; ">Model</h3>
 
<center><h4>LSTM Machine Learning Model</h4></center>
 
<center><h4>LSTM Machine Learning Model</h4></center>
 +
<form><fieldset>
 
<p style=" font-size:18px ; ">The LSTM model contained two lstm layers
 
<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
 
with 300 nodes each. The first lstm layer used dropout with a dropout
Line 26: Line 27:
 
hyperbolic tangent activation function. The output layer contained two
 
hyperbolic tangent activation function. The output layer contained two
 
nodes with a softmax activation function.<p>
 
nodes with a softmax activation function.<p>
 +
</feildset>
 +
</form>
 
<img src="https://static.igem.org/mediawiki/2017/e/ee/T--Florida_Atlantic--LSTMGraph.png">
 
<img src="https://static.igem.org/mediawiki/2017/e/ee/T--Florida_Atlantic--LSTMGraph.png">
  

Revision as of 21:16, 1 November 2017

HOME
TEAM
PROJECT
Description
Design
Experiments
InterLab
Model
Results
Attributions
Pictures
HUMAN PRACTICES
Silver HP
Gold HP
AWARDS
Model
Software
SAFETY
JUDGING FORM

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.