no code implementations • 15 Oct 2023 • Xiaoming Li, Hubert Normandin-Taillon, Chun Wang, Xiao Huang
In the realm of Mobility-on-Demand (MoD) systems, the forecasting of rider demand is a cornerstone for operational decision-making and system optimization.
no code implementations • 27 Feb 2023 • Hubert Normandin-Taillon, Frédéric Godin, Chun Wang
The pretraining method helps the RMDN avoid bad local minima during training and improves its robustness to the persistent NaN problem, as defined by Guillaumes [2017], which is often encountered with mixture density networks.