Distance Function Learning for Supervised Similarity Assessment
Abstract: Assessing the similarity between cases is a prerequisite for many case-based reasoning tasks. This chapter centers on distance function learning for supervised similarity assessment. First a framework for supervised similarity assessment is introduced. Second, three supervised distance function learning approaches from the areas of pattern classification, supervised clustering, and information retrieval are discussed, and their results for two supervised learning tasks will be explained and visualized. In each of these different areas, we show how the method can be applied to areas of case-based reasoning. Finally, a detailed literature survey will be given.
Loading