How do I create a Convolutional Newral Network?

superinhuman

I am new in Data Science and Rapidminer. Recently i was trying to implement CNN on my data set of Intrusion Detection System.

But I have failed to do it. Is there any operator for CNN like Neural Net?

Or there is any different way to implement it.

My XML code for the neural network model is below-

<?xml version="1.0" encoding="UTF-8"?><process version="9.5.001">
  <context>
    <input/>
    <output/>
    <macros/>
  </context>
  <operator activated="true" class="process" compatibility="9.5.001" expanded="true" name="Process">
    <parameter key="logverbosity" value="init"/>
    <parameter key="random_seed" value="2001"/>
    <parameter key="send_mail" value="never"/>
    <parameter key="notification_email" value=""/>
    <parameter key="process_duration_for_mail" value="30"/>
    <parameter key="encoding" value="SYSTEM"/>
    <process expanded="true">
      <operator activated="true" class="retrieve" compatibility="9.5.001" expanded="true" height="68" name="Retrieve WSN-DS" width="90" x="45" y="85">
        <parameter key="repository_entry" value="WSN-DS"/>
      </operator>
      <operator activated="true" class="set_role" compatibility="9.5.001" expanded="true" height="82" name="Set Role" width="90" x="179" y="85">
        <parameter key="attribute_name" value="Attack type"/>
        <parameter key="target_role" value="label"/>
        <list key="set_additional_roles"/>
      </operator>
      <operator activated="true" class="split_data" compatibility="9.5.001" expanded="true" height="103" name="Split Data" width="90" x="313" y="34">
        <enumeration key="partitions">
          <parameter key="ratio" value="0.8"/>
          <parameter key="ratio" value="0.2"/>
        </enumeration>
        <parameter key="sampling_type" value="automatic"/>
        <parameter key="use_local_random_seed" value="false"/>
        <parameter key="local_random_seed" value="1992"/>
      </operator>
      <operator activated="true" class="neural_net" compatibility="9.5.001" expanded="true" height="82" name="Neural Net" width="90" x="451" y="34">
        <list key="hidden_layers"/>
        <parameter key="training_cycles" value="200"/>
        <parameter key="learning_rate" value="0.01"/>
        <parameter key="momentum" value="0.9"/>
        <parameter key="decay" value="false"/>
        <parameter key="shuffle" value="true"/>
        <parameter key="normalize" value="true"/>
        <parameter key="error_epsilon" value="1.0E-4"/>
        <parameter key="use_local_random_seed" value="false"/>
        <parameter key="local_random_seed" value="1992"/>
      </operator>
      <operator activated="true" class="apply_model" compatibility="9.5.001" expanded="true" height="82" name="Apply Model" width="90" x="592" y="85">
        <list key="application_parameters"/>
        <parameter key="create_view" value="false"/>
      </operator>
      <operator activated="true" class="performance_classification" compatibility="9.5.001" expanded="true" height="82" name="Performance" width="90" x="726" y="85">
        <parameter key="main_criterion" value="accuracy"/>
        <parameter key="accuracy" value="true"/>
        <parameter key="classification_error" value="false"/>
        <parameter key="kappa" value="false"/>
        <parameter key="weighted_mean_recall" value="false"/>
        <parameter key="weighted_mean_precision" value="false"/>
        <parameter key="spearman_rho" value="false"/>
        <parameter key="kendall_tau" value="false"/>
        <parameter key="absolute_error" value="false"/>
        <parameter key="relative_error" value="false"/>
        <parameter key="relative_error_lenient" value="false"/>
        <parameter key="relative_error_strict" value="false"/>
        <parameter key="normalized_absolute_error" value="false"/>
        <parameter key="root_mean_squared_error" value="false"/>
        <parameter key="root_relative_squared_error" value="false"/>
        <parameter key="squared_error" value="false"/>
        <parameter key="correlation" value="false"/>
        <parameter key="squared_correlation" value="false"/>
        <parameter key="cross-entropy" value="false"/>
        <parameter key="margin" value="false"/>
        <parameter key="soft_margin_loss" value="false"/>
        <parameter key="logistic_loss" value="false"/>
        <parameter key="skip_undefined_labels" value="true"/>
        <parameter key="use_example_weights" value="true"/>
        <list key="class_weights"/>
      </operator>
      <connect from_op="Retrieve WSN-DS" from_port="output" to_op="Set Role" to_port="example set input"/>
      <connect from_op="Set Role" from_port="example set output" to_op="Split Data" to_port="example set"/>
      <connect from_op="Split Data" from_port="partition 1" to_op="Neural Net" to_port="training set"/>
      <connect from_op="Split Data" from_port="partition 2" to_op="Apply Model" to_port="unlabelled data"/>
      <connect from_op="Neural Net" from_port="model" to_op="Apply Model" to_port="model"/>
      <connect from_op="Apply Model" from_port="labelled data" to_op="Performance" to_port="labelled data"/>
      <connect from_op="Apply Model" from_port="model" to_port="result 1"/>
      <connect from_op="Performance" from_port="performance" to_port="result 2"/>
      <portSpacing port="source_input 1" spacing="0"/>
      <portSpacing port="sink_result 1" spacing="0"/>
      <portSpacing port="sink_result 2" spacing="0"/>
      <portSpacing port="sink_result 3" spacing="0"/>
    </process>
  </operator>
</process>

hughesfleming68

You need to download the Deep Learning DL4J extension. This is where the fun starts. You will need to know how to setup a convolution NN inside the deep learning operator. Your layer structure is very data dependent so this will require some experimentation. Follow the examples but start with simple architectures. ConvLayer+Fully Connected+Output layer then add a pooling layer to see the effect. You need to understand each layer in the context of your data. You may need one layer or several layers of convolutions depending on your data.

varunm1

Adding to @hughesfleming68 there is a sample process related to CNN when you download the Deep Learning extension from Rapidminer Market place (Extensions --> Market place). Once you install this DL extension, you can go to "Sample" Folder in Repository tab and in that you need to expand "Deep learning" folder where you can find "processes" folder that have "non-sequential data" folder. You can find CNN DL in 04 S&P 500 Regression using windowing.

sgenzer

hi @superinhuman welcome to the community. I guess my response is that, if you're new to data science and RapidMiner, working in deep learning / CNNs is probably not the best way to start. I'd recommend understanding the basics of machine learning and RapidMiner first with easier algorithms (decision trees is my preferred one for beginners) and then go from there. I've been doing this for literally years and I still do not use DL unless I absolutely need to - for all sorts of reasons.

https://academy.rapidminer.com/courses/machine-learning-professional-certification

Scott