Execution Time24.30s

Test: TMVA-DNN-Optimization-Cpu (Passed)
Build: master-x86_64-centos7-clang100-opt-no-rt-cxxmodules (olsnba08.cern.ch) on 2019-11-14 01:39:53
Repository revision: 32b17abcda23e44b64218a42d0ca69cb30cda7e0

Test Timing: Passed
Processors1

Show Command Line
Display graphs:

Test output
Testing optimization: (single precision)
Stochastic Gradient Descent:  Before Training: Mean Absolute Error = 0.819657, No of Epochs = 200, After Training: Mean Absolute error = 6.49561e-07
Stochastic Gradient Descent with momentum:  Before Training: Mean Absolute Error = 0.756144, No of Epochs = 174, After Training: Mean Absolute error = 1.79101e-07
Adam Optimizer:  Before Training: Mean Absolute Error = 0.832101, No of Epochs = 200, After Training: Mean Absolute error = 1.74562e-07
Adagrad Optimizer:  Before Training: Mean Absolute Error = 0.825577, No of Epochs = 200, After Training: Mean Absolute error = 1.2722e-07
RMSProp Optimizer without momentum:  Before Training: Mean Absolute Error = 0.947524, No of Epochs = 118, After Training: Mean Absolute error = 0.0103585
RMSProp Optimizer with momentum:  Before Training: Mean Absolute Error = 0.889969, No of Epochs = 200, After Training: Mean Absolute error = 0.015178
Adadelta Optimizer:  Before Training: Mean Absolute Error = 1.04005, No of Epochs = 154, After Training: Mean Absolute error = 0.00656743