E RNN

Recurrent neural networks (RNNs), particularly those hybridized with statistical methods, are being extensively researched for time series forecasting and other sequential data applications. Current efforts focus on improving RNN architectures like LSTMs and GRUs, exploring hybrid models such as ES-RNNs that combine RNNs with exponential smoothing, and developing efficient training methods to address challenges like vanishing gradients and computational cost. These advancements are yielding improved accuracy and interpretability in diverse fields, including finance (volatility estimation), music processing (singing voice synthesis), and epidemiology (disease modeling).

Papers

May 20, 2024

Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?
Yang Dai, Oubo Ma, Longfei Zhang, Xingxing Liang, Shengchao Hu, Mengzhu Wang, Shouling Ji, Jincai Huang, Li Shen
Offline Reinforcement Learning Trajectory Optimization Decision Transformer Mamba Based E RNN

September 13, 2023

From Deep Filtering to Deep Econometrics
Robert Stok, Paul Bilokon
Particle Filter Stochastic Volatility Deep Filter E RNN

July 28, 2023

Dynamic Analysis and an Eigen Initializer for Recurrent Neural Networks
Ran Dou, Jose Principe
Recurrent Neural Network Eigen Portfolio Well Trained E RNN

March 20, 2023

Late Meta-learning Fusion Using Representation Learning for Time Series Forecasting
Terence L. van Zyl
Time Series Forecasting Meta Training Model Fusion Meta Representation E RNN

May 9, 2022

Muskits: an End-to-End Music Processing Toolkit for Singing Voice Synthesis
Jiatong Shi, Shuai Guo, Tao Qian, Nan Huo, Tomoki Hayashi, Yuning Wu, Frank Xu, Xuankai Chang, Huazhe Li, Peter Wu, Shinji Watanabe, Qin Jin
Transfer Learning Speech Processing Audio Processing Singing Voice Synthesis E RNN End to End Singing Voice

March 7, 2022

Evaluating State of the Art, Forecasting Ensembles- and Meta-learning Strategies for Model Fusion
Pieter Cawood, Terence van Zyl
Global Evaluation Meta Learning Ensemble Learning Art Specific Information Ensemble Forecast Model Fusion Exponential Smoothing E RNN Ensemble Strategy

December 16, 2021

A Statistics and Deep Learning Hybrid Method for Multivariate Time Series Forecasting and Mortality Modeling
Thabang Mathonsi, Terence L. van Zyl
Multivariate Time Series Forecasting Hybrid Deep Learning Statistical Query Exponential Smoothing Forecast Combination Mortality Prediction Model E RNN

E RNN

Papers

Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?

From Deep Filtering to Deep Econometrics

Dynamic Analysis and an Eigen Initializer for Recurrent Neural Networks

Late Meta-learning Fusion Using Representation Learning for Time Series Forecasting

Muskits: an End-to-End Music Processing Toolkit for Singing Voice Synthesis

Evaluating State of the Art, Forecasting Ensembles- and Meta-learning Strategies for Model Fusion

A Statistics and Deep Learning Hybrid Method for Multivariate Time Series Forecasting and Mortality Modeling