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

March 30, 2022

Pay Attention to Hidden States for Video Deblurring: Ping-Pong Recurrent Neural Networks and Selective Non-Local Attention
JoonKyu Park, Seungjun Nah, Kyoung Mu Lee
Recurrent Neural Network Video Deblurring Hidden State RNN Architecture Pay Attention Non Local Attention RNN Cell Structure

March 28, 2022

UTSA NLP at SemEval-2022 Task 4: An Exploration of Simple Ensembles of Transformers, Convolutional, and Recurrent Neural Networks
Xingmeng Zhao, Anthony Rios
Deep Learning Model Transformer Megatron Decepticons Recurrent Neural Network Deep Convolutional Neural Network SemEval 2022 Task Bidirectional Long Short Term Memory Damo NLP Condescending Language Moderation Tool

March 25, 2022

March 24, 2022

March 23, 2022

Music Generation Using an LSTM
Michael Conner, Lucas Gral, Kevin Adams, David Hunger, Reagan Strelow, Alexander Neuwirth
Recurrent Neural Network Long Short Term Memory Music Generation

March 17, 2022

Recurrent Neural Networks for Forecasting Time Series with Multiple Seasonality: A Comparative Study
Grzegorz Dudek, Slawek Smyl, Paweł Pełka
Recurrent Neural Network Comparative Study Time Series Forecasting \Sigma}{\Delta}$ Low Pas RNN RNN Architecture Recurrent Unit

March 12, 2022

Recurrence-in-Recurrence Networks for Video Deblurring
Joonkyu Park, Seungjun Nah, Kyoung Mu Lee
Recurrent Neural Network Video Deblurring RNN Architecture Recurrence Network

March 10, 2022

Robustness Analysis of Classification Using Recurrent Neural Networks with Perturbed Sequential Input
Guangyi Liu, Arash Amini, Martin Takac, Nader Motee
Classification Code Recurrent Neural Network Input Perturbation Robustness Analysis Robustness Bound

March 8, 2022

LSTMSPLIT: Effective SPLIT Learning based LSTM on Sequential Time-Series Data
Lianlian Jiang, Yuexuan Wang, Wenyi Zheng, Chao Jin, Zengxiang Li, Sin G. Teo
Neural Network Recurrent Neural Network Long Short Term Memory Split Learning Sequential Data

March 3, 2022

March 2, 2022

March 1, 2022

Path sampling of recurrent neural networks by incorporating known physics
Sun-Ting Tsai, Eric Fields, Yijia Xu, En-Jui Kuo, Pratyush Tiwary
Recurrent Neural Network Generative AI Model Molecular Dynamic Physical Reasoning Recurrent Event Sample Path

February 27, 2022

ONE-NAS: An Online NeuroEvolution based Neural Architecture Search for Time Series Forecasting
Zimeng Lyu, Travis Desell
Recurrent Neural Network Neural Architecture Search Time Series Forecasting Wind Power SEMI SuperYOLO Na Hardware Accelerated NeuroEvolution

February 24, 2022

Recurrent Neural Network

Papers

Pay Attention to Hidden States for Video Deblurring: Ping-Pong Recurrent Neural Networks and Selective Non-Local Attention

UTSA NLP at SemEval-2022 Task 4: An Exploration of Simple Ensembles of Transformers, Convolutional, and Recurrent Neural Networks

A Hybrid Framework for Sequential Data Prediction with End-to-End Optimization

Embedding Recurrent Layers with Dual-Path Strategy in a Variant of Convolutional Network for Speaker-Independent Speech Separation

Automated Algorithm Selection: from Feature-Based to Feature-Free Approaches

Brain inspired neuronal silencing mechanism to enable reliable sequence identification

Music Generation Using an LSTM

Recurrent Neural Networks for Forecasting Time Series with Multiple Seasonality: A Comparative Study

Recurrence-in-Recurrence Networks for Video Deblurring

Robustness Analysis of Classification Using Recurrent Neural Networks with Perturbed Sequential Input

LSTMSPLIT: Effective SPLIT Learning based LSTM on Sequential Time-Series Data

Interpretable Latent Variables in Deep State Space Models

A Deep Neural Framework for Image Caption Generation Using GRU-Based Attention Mechanism

Deep Q-network using reservoir computing with multi-layered readout

Parallel Spatio-Temporal Attention-Based TCN for Multivariate Time Series Prediction

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

Path sampling of recurrent neural networks by incorporating known physics

ONE-NAS: An Online NeuroEvolution based Neural Architecture Search for Time Series Forecasting

Unfolding AIS transmission behavior for vessel movement modeling on noisy data leveraging machine learning

Can deep neural networks learn process model structure? An assessment framework and analysis