Search Results for author:
Found 2 papers, 0 papers with code
XRMDN: An Extended Recurrent Mixture Density Network for Short-Term Probabilistic Rider Demand Forecasting with High Volatility
In the realm of Mobility-on-Demand (MoD) systems, the forecasting of rider demand is a cornerstone for operational decision-making and system optimization.
Linear pretraining in recurrent mixture density networks
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.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
