Execution Time1.11s

Test: TMVA-DNN-Optimization-Cpu (Passed)
Build: master-x86_64-fedora28-gcc8 (sft-fedora-28-1.cern.ch) on 2019-11-14 01:14:20

Test Timing: Passed
Processors1

Show Command Line
Display graphs:

Test output
Testing optimization: (single precision)
Stochastic Gradient Descent:  Before Training: Mean Absolute Error = 0.786734, No of Epochs = 200, After Training: Mean Absolute error = 5.90966e-07
Stochastic Gradient Descent with momentum:  Before Training: Mean Absolute Error = 0.721258, No of Epochs = 200, After Training: Mean Absolute error = 1.54013e-07
Adam Optimizer:  Before Training: Mean Absolute Error = 0.89539, No of Epochs = 200, After Training: Mean Absolute error = 1.79485e-07
Adagrad Optimizer:  Before Training: Mean Absolute Error = 0.919295, No of Epochs = 200, After Training: Mean Absolute error = 9.45332e-08
RMSProp Optimizer without momentum:  Before Training: Mean Absolute Error = 0.763704, No of Epochs = 118, After Training: Mean Absolute error = 0.0125946
RMSProp Optimizer with momentum:  Before Training: Mean Absolute Error = 0.84282, No of Epochs = 200, After Training: Mean Absolute error = 0.0194977
Adadelta Optimizer:  Before Training: Mean Absolute Error = 1.06584, No of Epochs = 159, After Training: Mean Absolute error = 0.0216536