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

October 11, 2023

October 9, 2023

Molecular De Novo Design through Transformer-based Reinforcement Learning
Pengcheng Xu, Tao Feng, Tianfan Fu, Siddhartha Laghuvarapu, Jimeng Sun
Reinforcement Learning Recurrent Neural Network RNN Model Transformer Based Generative De Novo

October 5, 2023

October 4, 2023

Graph Neural Networks and Time Series as Directed Graphs for Quality Recognition
Angelica Simonetti, Ferdinando Zanchetta
Graph Neural Network Time Series Recurrent Neural Network Recognition Rate Temporal Convolutional Network Directed Graph Geometric Deep Learning Model Temporal Topological

October 3, 2023

Episodic Memory Theory for the Mechanistic Interpretation of Recurrent Neural Networks
Arjun Karuvally, Peter Delmastro, Hava T. Siegelmann
Recurrent Neural Network Mechanistic Interpretation Neural Memory

October 2, 2023

September 28, 2023

September 26, 2023

On the Computational Complexity and Formal Hierarchy of Second Order Recurrent Neural Networks
Ankur Mali, Alexander Ororbia, Daniel Kifer, Lee Giles
Recurrent Neural Network Second Order Part Whole Hierarchy Computational Complexity Traditional RNNs

September 25, 2023

Detach-ROCKET: Sequential feature selection for time series classification with random convolutional kernels
Gonzalo Uribarri, Federico Barone, Alessio Ansuini, Erik Fransén
Recurrent Neural Network Time Series Data Time Series Classification Random Convolution

September 22, 2023

September 21, 2023

Parallelizing non-linear sequential models over the sequence length
Yi Heng Lim, Qi Zhu, Joshua Selfridge, Muhammad Firmansyah Kasim
Recurrent Neural Network Gated Recurrent Unit Sequential Model Sequence Length Training Bottleneck

September 19, 2023

Hybrid State Space-based Learning for Sequential Data Prediction with Joint Optimization
Mustafa E. Aydın, Arda Fazla, Suleyman S. Kozat
LeArning Abstract Time Series Recurrent Neural Network Joint Optimization Nonlinear Prediction Sequential Prediction State Space Representation

September 14, 2023

Comparative Assessment of Markov Models and Recurrent Neural Networks for Jazz Music Generation
Conrad Hsu, Ross Greer
Generative Model Recurrent Neural Network Comparative Evaluation Melody Generation

September 13, 2023

Efficient quantum recurrent reinforcement learning via quantum reservoir computing
Samuel Yen-Chi Chen
Recurrent Neural Network Long Short Term Memory Quantum Reinforcement Learning Reservoir Dynamic Quantum Reservoir

September 7, 2023

Brief technical note on linearizing recurrent neural networks (RNNs) before vs after the pointwise nonlinearity
Marino Pagan, Adrian Valente, Srdjan Ostojic, Carlos D. Brody
Recurrent Neural Network Technical Report Reverse Graph Linearization RNN Behavior

Recurrent Neural Network

Papers

Recurrent networks recognize patterns with low-dimensional oscillations

Growing Brains: Co-emergence of Anatomical and Functional Modularity in Recurrent Neural Networks

Molecular De Novo Design through Transformer-based Reinforcement Learning

Deep Geometric Learning with Monotonicity Constraints for Alzheimer's Disease Progression

Sparse Deep Learning for Time Series Data: Theory and Applications

Graph Neural Networks and Time Series as Directed Graphs for Quality Recognition

Episodic Memory Theory for the Mechanistic Interpretation of Recurrent Neural Networks

Memory-efficient particle filter recurrent neural network for object localization

Contraction Properties of the Global Workspace Primitive

Message Propagation Through Time: An Algorithm for Sequence Dependency Retention in Time Series Modeling

Nonlinear MPC design for incrementally ISS systems with application to GRU networks

On the Computational Complexity and Formal Hierarchy of Second Order Recurrent Neural Networks

Detach-ROCKET: Sequential feature selection for time series classification with random convolutional kernels

Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks

Recurrent Temporal Revision Graph Networks

Parallelizing non-linear sequential models over the sequence length

Hybrid State Space-based Learning for Sequential Data Prediction with Joint Optimization

Comparative Assessment of Markov Models and Recurrent Neural Networks for Jazz Music Generation

Efficient quantum recurrent reinforcement learning via quantum reservoir computing

Brief technical note on linearizing recurrent neural networks (RNNs) before vs after the pointwise nonlinearity