A Hierarchical Mixture Density Network

October 23, 2019 · Declared Dead · 🏛 International Conference on Neural Information Processing

👻 CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Fan Yang, Jaymar Soriano, Takatomi Kubo, Kazushi Ikeda arXiv ID 1910.13523 Category cs.CV: Computer Vision Cross-listed cs.MM, eess.SP Citations 3 Venue International Conference on Neural Information Processing Last Checked 3 months ago
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.
Community shame:
Not yet rated
📄 View on arXiv 🌐 View on ar5iv 📑 PDF 🎉 Report Code Found
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

📜 Similar Papers

In the same crypt — Computer Vision

Died the same way — 👻 Ghosted