Timescale Separation in Recurrent Neural Networks

DOI10.1162/NECO_a_00740zbMath1473.68142OpenAlexW2157135189WikidataQ50594023 ScholiaQ50594023MaRDI QIDQ5380251

Thomas Flynn

Publication date: 4 June 2019

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1162/neco_a_00740

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)

Related Items (2)

Forward sensitivity analysis for contracting stochastic systems ⋮ A persistent adjoint method with dynamic time-scaling and an application to mass action kinetics

Cites Work

• Unnamed Item
• Reservoir computing approaches to recurrent neural network training
• On nonlinear difference and differential equations
• Connectionist learning of belief networks
• On contraction analysis for non-linear systems
• Dynamic behaviors of memristor-based recurrent neural networks with time-varying delays
• On partial contraction analysis for coupled nonlinear oscillators
• An Efficient Learning Procedure for Deep Boltzmann Machines
• Dynamic properties of neural networks with adapting synapses
• On the convergence of markovian stochastic algorithms with rapidly decreasing ergodicity rates
• Differential-algebraic equations and singular perturbation methods in recurrent neural learning
• Gradient Convergence in Gradient methods with Errors
• Nonlinear Systems Analysis
• Contractive Systems with Inputs
• A Contraction Theory Approach to Singularly Perturbed Systems

This page was built for publication: Timescale Separation in Recurrent Neural Networks