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

December 18, 2022

Hidden State Approximation in Recurrent Neural Networks Using Continuous Particle Filtering
Dexun Li
Recurrent Neural Network Long Short Term Memory Encoder Decoder Model Hidden State Traditional Recurrent Neural Network

December 16, 2022

December 13, 2022

December 12, 2022

Robust Recurrent Neural Network to Identify Ship Motion in Open Water with Performance Guarantees -- Technical Report
Daniel Frank, Decky Aspandi Latif, Michael Muehlebach, Benjamin Unger, Steffen Staab
Neural Network Recurrent Neural Network Technical Report Underwater Environment Performance Guarantee Ship Motion Linear Time Invariant System Unknown Nonlinear System

December 10, 2022

State-Regularized Recurrent Neural Networks to Extract Automata and Explain Predictions
Cheng Wang, Carolin Lawrence, Mathias Niepert
Recurrent Neural Network Recurrent Network Traditional RNNs Explainable Prediction Automaton Extraction

December 9, 2022

December 7, 2022

Expressive architectures enhance interpretability of dynamics-based neural population models
Andrew R. Sedler, Christopher Versteeg, Chethan Pandarinath
Inherent Interpretability Recurrent Neural Network Latent Dynamic Neural Dynamic Chaotic Attractor

November 30, 2022

Correlation recurrent units: A novel neural architecture for improving the predictive performance of time-series data
Sunghyun Sim, Dohee Kim, Hyerim Bae
Recurrent Neural Network Time Series Forecasting Time Series Data Neural Network Architecture Predictive Performance Recurrent Unit Time Series Decomposition

November 29, 2022

November 28, 2022

Beyond S-curves: Recurrent Neural Networks for Technology Forecasting
Alexander Glavackij, Dimitri Percia David, Alain Mermoud, Angelika Romanou, Karl Aberer
Recurrent Neural Network Time Series Forecasting Forecasting Performance Forecast Utterance Aggregated Curve

November 25, 2022

Minimal Width for Universal Property of Deep RNN
Chang hoon Song, Geonho Hwang, Jun ho Lee, Myungjoo Kang
Recurrent Neural Network Universal Approximation K$ Universality Minimum Width Deep Narrow

November 22, 2022

A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithms
Danimir T. Doncevic, Alexander Mitsos, Yue Guo, Qianxiao Li, Felix Dietrich, Manuel Dahmen, Ioannis G. Kevrekidis
Recurrent Neural Network Meta Learning Architecture Design Iterative Algorithm Recursive Neural Network Runge Kutta

November 21, 2022

LSTM based models stability in the context of Sentiment Analysis for social media
Bousselham El Haddaoui, Raddouane Chiheb, Rdouan Faizi, Abdellatif El Afia
Sentiment Analysis Recurrent Neural Network Long Short Term Memory Social Medium Context Information Model Stability

November 17, 2022

Learning to Control Rapidly Changing Synaptic Connections: An Alternative Type of Memory in Sequence Processing Artificial Neural Networks
Kazuki Irie, Jürgen Schmidhuber
LeArning Abstract Recurrent Neural Network Memory Trace Short Term Memory Artificial Neuron RNN Architecture Synaptic Connectivity

November 15, 2022

Universal Time-Uniform Trajectory Approximation for Random Dynamical Systems with Recurrent Neural Networks
Adrian N. Bishop
Recurrent Neural Network Deep Recurrent Neural Network Trajectory Corner Case Random Dynamical System

November 11, 2022

Re-visiting Reservoir Computing architectures optimized by Evolutionary Algorithms
Sebastián Basterrech, Tarun Kumar Sharma
Recurrent Neural Network Evolutionary Algorithm Reservoir Computing

Recurrent Neural Network

Papers

Hidden State Approximation in Recurrent Neural Networks Using Continuous Particle Filtering

Learnable Commutative Monoids for Graph Neural Networks

Preventing RNN from Using Sequence Length as a Feature

Temporal Weights

Can recurrent neural networks learn process model structure?

Robust Recurrent Neural Network to Identify Ship Motion in Open Water with Performance Guarantees -- Technical Report

State-Regularized Recurrent Neural Networks to Extract Automata and Explain Predictions

Emergent Computations in Trained Artificial Neural Networks and Real Brains

Decomposing a Recurrent Neural Network into Modules for Enabling Reusability and Replacement

Expressive architectures enhance interpretability of dynamics-based neural population models

Correlation recurrent units: A novel neural architecture for improving the predictive performance of time-series data

Testing GLOM's ability to infer wholes from ambiguous parts

Symmetry Detection in Trajectory Data for More Meaningful Reinforcement Learning Representations

Beyond S-curves: Recurrent Neural Networks for Technology Forecasting

Minimal Width for Universal Property of Deep RNN

A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithms

LSTM based models stability in the context of Sentiment Analysis for social media

Learning to Control Rapidly Changing Synaptic Connections: An Alternative Type of Memory in Sequence Processing Artificial Neural Networks

Universal Time-Uniform Trajectory Approximation for Random Dynamical Systems with Recurrent Neural Networks

Re-visiting Reservoir Computing architectures optimized by Evolutionary Algorithms