Timescale separation in recurrent neural networks

DOI10.1162/NECO_A_00740MaRDI QIDQ5380251zbMATH OpenOpenAlexWikidataFDO

Authors 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)

Recommendations

• scientific article; zbMATH DE number 1928803
• A learning result for continuous-time recurrent neural networks
• A learning algorithm to teach spatiotemporal patterns to recurrent neural networks
• Supervised Learning in a Recurrent Network of Rate-Model Neurons Exhibiting Frequency Adaptation
• Stable and convergent dynamics for discrete-time recurrent networks

Cites work

• A Contraction Theory Approach to Singularly Perturbed Systems
• An efficient learning procedure for deep Boltzmann machines
• Connectionist learning of belief networks
• Contractive Systems with Inputs
• Differential-algebraic equations and singular perturbation methods in recurrent neural learning
• Dynamic behaviors of memristor-based recurrent neural networks with time-varying delays
• Dynamic properties of neural networks with adapting synapses
• Gradient Convergence in Gradient methods with Errors
• scientific article; zbMATH DE number 1928803 (Why is no real title available?)
• Nonlinear Systems Analysis
• On contraction analysis for non-linear systems
• On nonlinear difference and differential equations
• On partial contraction analysis for coupled nonlinear oscillators
• On the convergence of markovian stochastic algorithms with rapidly decreasing ergodicity rates
• Reservoir computing approaches to recurrent neural network training

Cited in

(9)

• Resonant spatiotemporal learning in large random recurrent networks
• A persistent adjoint method with dynamic time-scaling and an application to mass action kinetics
• Energy-Time Tradeoff in Recurrent Neural Nets
• Equivalence of equilibrium propagation and recurrent backpropagation
• scientific article; zbMATH DE number 1928803 (Why is no real title available?)
• Finite-size effects in separable recurrent neural networks
• A unified framework of online learning algorithms for training recurrent neural networks
• scientific article; zbMATH DE number 7155814 (Why is no real title available?)
• Forward sensitivity analysis for contracting stochastic systems

This page was built for publication: Timescale separation in recurrent neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5380251)