Absolute Error

Top 

Absolute Error

The absolute error is the absolute value of the difference between the value the network is predicting for an output and the actual value of that output.

 

Mean Absolute Error - This is the mean over all patterns of the absolute value of the actual minus predicted, i.e., the mean of |actual - predicted|.

 

Min Absolute Error - This is the minimum of |actual - predicted| of all patterns.

 

Max Absolute Error - This is the maximum of |actual - predicted| of all patterns.