Hierarchical Neural Networks Utilising Dempster-Shafer Evidence Theory

Abstract. Hierarchical neural networks show many benefits when employed for classification problems even when only simple methods analogous to decision trees are used to retrieve the classification result. More complex ways of evaluating the hierarchy output that take into account the complete information the hierarchy provides yield improved classification results. Due to the hierarchical output space decomposition that is inherent to hierarchical neural networks the usage of DempsterShafer evidence theory suggests itself as it allows for the representation nce at different levels of abstraction. Moreover, it provides the possibility to differentiate between uncertainty and ignorance. The proposed approach has been evaluated using three different data sets and showed consistently improved classification results compared to the simple decision-tree-like retrieval method.

• Type: Conference
• Year: 2006
• Where: ANNPR
• Authors: Rebecca Fay, Friedhelm Schwenker, Christian Thiel, Günther Palm
• Keywords: ANNPR 2006, Hierarchical Neural Networks, Hierarchical Output Space, Neural Networks, Yield Improved Classification