A Hierarchical Mixture Density Network
This addresses indoor positioning challenges, but appears incremental as it builds on existing mixture density networks.
The paper tackles the problem of modeling complex relationships among three correlated variables, specifically a two-layer hierarchical many-to-many mapping, by proposing a Hierarchical Mixture Density Network (HMDN) and applies it to an indoor positioning problem, showing its benefit.
The relationship among three correlated variables could be very sophisticated, as a result, we may not be able to find their hidden causality and model their relationship explicitly. However, we still can make our best guess for possible mappings among these variables, based on the observed relationship. One of the complicated relationships among three correlated variables could be a two-layer hierarchical many-to-many mapping. In this paper, we proposed a Hierarchical Mixture Density Network (HMDN) to model the two-layer hierarchical many-to-many mapping. We apply HMDN on an indoor positioning problem and show its benefit.