Recurrent Neural Network

Recurrent Neural Networks (RNNs) are a class of neural networks designed to process sequential data by maintaining an internal state that is updated over time. Current research focuses on improving RNN efficiency and stability, exploring variations like LSTMs and GRUs, and investigating their application in diverse fields such as time series forecasting, natural language processing, and dynamical systems modeling. This includes developing novel architectures like selective state space models for improved memory efficiency and exploring the use of RNNs in conjunction with other architectures, such as transformers and convolutional neural networks. The resulting advancements have significant implications for various applications requiring sequential data processing, offering improved accuracy, efficiency, and interpretability.

Papers

February 13, 2023

Soft Continuum Actuator Tip Position and Contact Force Prediction, Using Electrical Impedance Tomography and Recurrent Neural Networks
Amirhosein Alian, George Mylonas, James Avery
Recurrent Neural Network Soft Robot Continuum Robot Contact Force Electrical Impedance Tomography

February 10, 2023

Satellite Anomaly Detection Using Variance Based Genetic Ensemble of Neural Networks
Mohammad Amin Maleki Sadr, Yeying Zhu, Peng Hu
Neural Network Recurrent Neural Network Bayesian Neural Network Ensemble Model Ensemble Based

February 9, 2023

NeuKron: Constant-Size Lossy Compression of Sparse Reorderable Matrices and Tensors
Taehyung Kwon, Jihoon Ko, Jinhong Jung, Kijung Shin
Recurrent Neural Network Lossy Compression Tensor Type Calculus Sparse Matrix

February 7, 2023

Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNs
Yu Duan, Zhongfan Jia, Qian Li, Yi Zhong, Kaisheng Ma
Recurrent Neural Network Plasticity Rule Fast Learning Hebbian Plasticity Hebbian Model

January 30, 2023

Quantifying and maximizing the information flux in recurrent neural networks
Claus Metzner, Marius E. Yamakou, Dennis Voelkl, Achim Schilling, Patrick Krauss
Recurrent Neural Network Information Flow Dynamical Network

January 20, 2023

Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks
Khurram Javed, Haseeb Shah, Rich Sutton, Martha White
Recurrent Neural Network Back Propagation Recurrent Network Real Time Recurrent Learning Geometric Neural Network

January 19, 2023

Efficient Pricing and Hedging of High Dimensional American Options Using Recurrent Networks
Andrew Na, Justin Wan
Recurrent Neural Network Recurrent Network Deep Recurrent Neural Network Hedging Strategy Neural Network Framework

January 16, 2023

BayesSpeech: A Bayesian Transformer Network for Automatic Speech Recognition
Will Rieger
Automatic Speech Recognition Recurrent Neural Network RNN Model Probabilistic Transformer

January 13, 2023

Building a Fuel Moisture Model for the Coupled Fire-Atmosphere Model WRF-SFIRE from Data: From Kalman Filters to Recurrent Neural Networks
J. Mandel, J. Hirschi, A. K. Kochanski, A. Farguell, J. Haley, D. V. Mallia, B. Shaddy, A. A. Oberai, K. A. Hilburn
Raw Data Recurrent Neural Network Differential Equation Kalman Filter Data Assimilation Fighting Fire Workflow Composition Moisture Content Mesoscale Structure

January 12, 2023

January 2, 2023

A Concurrent CNN-RNN Approach for Multi-Step Wind Power Forecasting
Syed Kazmi, Berk Gorgulu, Mucahit Cevik, Mustafa Gokce Baydogan
Recurrent Neural Network Numerical Weather Prediction RNN Architecture Global Forecasting Wind Power Forecasting Concurrent Transmission

December 30, 2022

PAC-Bayesian-Like Error Bound for a Class of Linear Time-Invariant Stochastic State-Space Models
Deividas Eringis, John Leth, Zheng-Hua Tan, Rafal Wisniewski, Mihaly Petreczky
Recurrent Neural Network State Space Model True Class Stochastic Dynamical System Probably Approximately Correct PAC Bayes Bound

December 29, 2022

Macro-block dropout for improved regularization in training end-to-end speech recognition models
Chanwoo Kim, Sathish Indurti, Jinhwan Park, Wonyong Sung
End to End Recurrent Neural Network Structured Dropout Recurrent Neural Network Transducer Regularization Based Method

December 28, 2022

Continuous Depth Recurrent Neural Differential Equations
Srinivas Anumasa, Geetakrishnasai Gunapati, P. K. Srijith
Recurrent Neural Network RNN Model Continuous Depth

December 22, 2022

Training Integer-Only Deep Recurrent Neural Networks
Vahid Partovi Nia, Eyyüb Sari, Vanessa Courville, Masoud Asgharian
Language Model Recurrent Neural Network Integer Only Training

December 20, 2022

December 18, 2022

Recurrent Neural Network

Papers

Soft Continuum Actuator Tip Position and Contact Force Prediction, Using Electrical Impedance Tomography and Recurrent Neural Networks

Satellite Anomaly Detection Using Variance Based Genetic Ensemble of Neural Networks

NeuKron: Constant-Size Lossy Compression of Sparse Reorderable Matrices and Tensors

Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNs

Quantifying and maximizing the information flux in recurrent neural networks

Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks

Efficient Pricing and Hedging of High Dimensional American Options Using Recurrent Networks

BayesSpeech: A Bayesian Transformer Network for Automatic Speech Recognition

Building a Fuel Moisture Model for the Coupled Fire-Atmosphere Model WRF-SFIRE from Data: From Kalman Filters to Recurrent Neural Networks

Explicit Context Integrated Recurrent Neural Network for Sensor Data Applications

LiteLSTM Architecture Based on Weights Sharing for Recurrent Neural Networks

A Concurrent CNN-RNN Approach for Multi-Step Wind Power Forecasting

PAC-Bayesian-Like Error Bound for a Class of Linear Time-Invariant Stochastic State-Space Models

Macro-block dropout for improved regularization in training end-to-end speech recognition models

Continuous Depth Recurrent Neural Differential Equations

Training Integer-Only Deep Recurrent Neural Networks

Pain level and pain-related behaviour classification using GRU-based sparsely-connected RNNs

Empirical Analysis of Limits for Memory Distance in Recurrent Neural Networks

PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanism

Contextually Enhanced ES-dRNN with Dynamic Attention for Short-Term Load Forecasting