A Hierarchical Mixture Density Network

TL;DR

This paper introduces a Hierarchical Mixture Density Network (HMDN) designed to model complex two-layer hierarchical relationships among three correlated variables, demonstrated through an indoor positioning application.

Contribution

The paper proposes a novel HMDN architecture to effectively model hierarchical many-to-many mappings among variables, addressing complex relationships that are hard to explicitly model.

Findings

HMDN successfully models hierarchical relationships in data.

Application to indoor positioning shows improved performance.

Demonstrates effectiveness in capturing complex variable interactions.

Abstract

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.