Windowed active sampling for reliable neural learning

The composition of the example set has a major impact on the quality of neural learning. The popular approach is focused on extensive pre-processing to bridge the representation gap between process measurement and neural presentation. In contrast, windowed active sampling attempts to solve these problems in an on-line interaction between problem selection and learning. This paper provides an unified view on the conflicts that may pop-up within a neural network in the presence of ill-ordered data. It is marked that such conflicts become noticeable form the operational learning characteristics. An adaptive operational strategy is proposed that closes the representing gap and its working is illustrated in the diagnosis of power generators