Acquiring and Conditioning Network Data

Training a neural network involves a number of considerations in getting from the process to be modeled to the actual set of network training exemplars. These considerations include the following (Stein, 1993): Data Specification: Deciding on what variables should be includedData Collection: Collecting samples from the included variablesData Inspection: Inspecting the data for characteristic and anomalous featuresData Conditioning: Preprocessing the data to extract features, correct for anomalies, or to reduce the volume of data