Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network

DOI10.1016/j.physd.2019.132306OpenAlexW2885195348WikidataQ126318043 ScholiaQ126318043MaRDI QIDQ2116251

Alex Sherstinsky

Publication date: 16 March 2022

Published in: Physica D (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1808.03314

zbMATH Keywords

LSTMRNNconvolutional input context windowsexternal input gateRNN unfoldingRNN unrolling

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) General theory of functional-differential equations (34K05)

Related Items (15)

Numerical solution of the stochastic neural field equation with applications to working memory ⋮ Recursive approach for multiple step-ahead software fault prediction through long short-term memory (LSTM) ⋮ Neural-network learning of SPOD latent dynamics ⋮ Data-driven synchronization-avoiding algorithms in the explicit distributed structural analysis of soft tissue ⋮ A machine‐learning based ConvLSTM architecture for NDVI forecasting ⋮ A framework for machine learning of model error in dynamical systems ⋮ Unnamed Item ⋮ The Mori-Zwanzig formulation of deep learning ⋮ Depth asynchronous time delay reservoir for nonlinear time series forecasting task ⋮ Unnamed Item ⋮ Comparison of recursive neural network and Markov chain models in facies inversion ⋮ Predicting critical transitions in multiscale dynamical systems using reservoir computing ⋮ A prediction model of aquaculture water quality based on multiscale decomposition ⋮ Task-Aware Verifiable RNN-Based Policies for Partially Observable Markov Decision Processes ⋮ Bridging the gap: machine learning to resolve improperly modeled dynamics

Uses Software

• LSTM
• NumPy
• AntisymmetricRNN
• torchdiffeq

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Supervised sequence labelling with recurrent neural networks.
• Temporal-kernel recurrent neural networks
• Cellular neural networks: theory
• On stability and equilibria of the M-lattice
• Stable architectures for deep neural networks
• Equation of State Calculations by Fast Computing Machines
• On the Use of Delay Equations in Engineering Applications
• Neurons with graded response have collective computational properties like those of two-state neurons.

This page was built for publication: Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network