paper-with-me

Papers

Linear pretraining in recurrent mixture density networks

2023-02-27 · Hubert Normandin-Taillon, Frédéric Godin, Chun Wang

We present a method for pretraining a recurrent mixture density network (RMDN). We also propose a slight modification to the architecture of the RMDN-GARCH proposed by Nikolaev et al. [2012]. 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. Such problem consists in frequently obtaining "Not a number" (NaN) values during training. The pretraining method proposed resolves these issues by training the linear nodes in the hidden layer of the RMDN before starting including non-linear node updates. Such an approach improves the performance of the RMDN and ensures it surpasses that of the GARCH model, which is the RMDN's linear counterpart.

📄 PDF Abstract BibTeX arXiv:2302.14141

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

FRMDN: Flow-based Recurrent Mixture Density Network

2020-08-05 · Seyedeh Fatemeh Razavi, Reshad Hosseini, Tina Behzad

The class of recurrent mixture density networks is an important class of probabilistic models used extensively in sequence modeling and sequence-to-sequence mapping applications. In this class of models, the density of a…

Supervised and Semi-supervised Deep Probabilistic Models for Indoor Positioning Problems

2019-11-22 · Weizhu Qian, Fabrice Lauri, Franck Gechter

Predicting smartphone users location with WiFi fingerprints has been a popular research topic recently. In this work, we propose two novel deep learning-based models, the convolutional mixture density recurrent neural ne…

Convolutional Mixture Density Recurrent Neural Network for Predicting User Location with WiFi Fingerprints

2019-11-21 · Weizhu Qian, Fabrice Lauri, Franck Gechter

Predicting smartphone users activity using WiFi fingerprints has been a popular approach for indoor positioning in recent years. However, such a high dimensional time-series prediction problem can be very tricky to solve…

Time SeriesTime Series AnalysisTime Series Prediction

Attention-based Mixture Density Recurrent Networks for History-based Recommendation

2017-09-22 · Tian Wang, Kyunghyun Cho

The goal of personalized history-based recommendation is to automatically output a distribution over all the items given a sequence of previous purchases of a user. In this work, we present a novel approach that uses a r…

MD-NOMAD: Mixture density nonlinear manifold decoder for emulating stochastic differential equations and uncertainty propagation

2024-04-24 · Akshay Thakur, Souvik Chakraborty

We propose a neural operator framework, termed mixture density nonlinear manifold decoder (MD-NOMAD), for stochastic simulators. Our approach leverages an amalgamation of the pointwise operator learning neural architectu…

DecoderOperator learning