講座內(nèi)容：Data are the blood life of today’ssociety. The diversity of data isenormous. The quality of data including their comprehensive and multifacetedcharacterization becomes of paramount importance and is central to further dataanalysis and processing.

In this presentation, we cover a suite ofselected insights into data quality and elaborate on their quantification. Thetwo central issues involving coping with incomplete data (invoking dataimputation) and imbalanced data are discussed.

In addressing these issues and deliveringalgorithmically sound solutions, we advocate a central role of informationgranularity being played in dealing with the two above stated problems andyielding the results quantified in terms of information granules.

Revealing interpretable and conceptually stable associations(relationships) within data form another central item on the agenda of dataanalytics. We show how granular mappings engaging granular parameter spaces aredeveloped and assessed. Associativerelationships constructed in terms of granular bidirectional andmultidirectional associative memories are investigated. We also developgranular autoencoders and stacked granular autoencoders.