Activity Stream

[Preprocessing testing and training input file]

agreed. what's the question?

[Calculation of Training Errors]

Usually that is the difference between the expected and calculated values. Sometimes it is used as a scaling factor (such as learning rate) for the weight matrix update.

[Optimum Activation Function]

Should there be an end difference for the correlation co-efficient based on the activation function? I can get 0.94 for tanh, but only 0.64 for logistic.

[Preprocessing testing and training input file]

When the testing and training data are different and the respective input files are not standardized, in that case is this the right way of preprocessing:

preprocess   non_standardized_training_input_file.txt        non_standardized_training_input_file.txt           1             standardized_training_input_file.txt

followed by

preprocess   non_standardized_training_input_file.txt        non_standardized_testing_input_file.txt           1             standardized_testing_input_file.txt      

 

[Calculation of Training Errors]

How is training error calculated while training the network?