Sensitivity analysis for a single sample

• Switch to Evaluation panel

• Choose the file in Evaluation files section:

  • If the file was supplied earlier, it is already listed in Evaluation files

  • To add a new file for evaluation, press + in Additional section of Evaluation files

  • For Sensitivity analysis, the output file is not required

• Once the input file clicked (or a pair input/output), choose a sample to study using Sample slider

• Click on one of the output neurons (representing output features) on the plot of the neural network in the Network sensitivity section

• Each neuron becomes colored according to the sensitivity of the chosen output neurons with respect to this neuron

• For the input neurons (representing the input features): click on an input neuron to get the calculated value of sensitivity in addition to color

An example of the sensitivity analysis for a single sample:

Tabular network sensitivity for a single sample. Regression test case: Energy consumption.

Note

By default, the Network sensitivity is performed with the last model available in the checkpoint. Use the checkpoint slider in the bottom to choose any other available model.